Climate Change (CC) is a pressing topic of global importance, attracting increasing attention across research fields, from social sciences to Natural Language Processing (NLP). CC is also discussed in various settings and communication platforms, from academic publications to social media forums. Understanding who and what is mentioned in such data is a first critical step to gaining new insights into CC. We present CLIMATELI (CLIMATe Entity LInking), the first manually annotated CC dataset that links 3,087 entity spans to Wikipedia. Using CLIMATELI (CLIMATe Entity LInking), we evaluate existing entity linking (EL) systems on the CC topic across various genres and propose automated filtering methods for CC entities. We find that the performance of EL models notably lags behind humans at both token and entity levels. Testing within the scope of retaining or excluding non-nominal and/or non-CC entities particularly impacts the models’ performances.

In this work, we analyze the uncertainty that is inherently present in the labels used for supervised machine learning in natural language inference (NLI). In cases where multiple annotations per instance are available, neither the majority vote nor the frequency of individual class votes is a trustworthy representation of the labeling uncertainty. We propose modeling the votes via a Bayesian mixture model to recover the data-generating process, i.e., the “true” latent classes, and thus gain insight into the class variations. This will enable a better understanding of the confusion happening during the annotation process. We also assess the stability of the proposed estimation procedure by systematically varying the numbers of i) instances and ii) labels. Thereby, we observe that few instances with many labels can predict the latent class borders reasonably well, while the estimation fails for many instances with only a few labels. This leads us to conclude that multiple labels are a crucial building block for properly analyzing label uncertainty.

Named Entity Recognition (NER) is a key information extraction task with a long-standing tradition. While recent studies address and aim to correct annotation errors via re-labeling efforts, little is known about the sources of label variation, such as text ambiguity, annotation error, or guideline divergence. This is especially the case for high-quality datasets and beyond English CoNLL03. This paper studies disagreements in expert-annotated named entity datasets for three varieties: English, Danish, and DialectX. We show that text ambiguity and artificial guideline changes are dominant factors for diverse annotations among high-quality revisions. We survey student annotations on a subset of difficult entities and substantiate the feasibility and necessity of manifold annotations for understanding named entity ambiguities from a distributional perspective.

In Natural Language Processing, entity linking (EL) has centered around Wikipedia, but yet remains underexplored for the job market domain. Disambiguating skill mentions can help us get insight into the current labor market demands. In this work, we are the first to explore EL in this domain, specifically targeting the linkage of occupational skills to the ESCO taxonomy (le Vrang et al., 2014). Previous efforts linked coarse-grained (full) sentences to a corresponding ESCO skill. In this work, we link more fine-grained span-level mentions of skills. We tune two high-performing neural EL models, a bi-encoder (Wu et al., 2020) and an autoregressive model (Cao et al., 2021), on a synthetically generated mention–skill pair dataset and evaluate them on a human-annotated skill-linking benchmark. Our findings reveal that both models are capable of linking implicit mentions of skills to their correct taxonomy counterparts. Empirically, BLINK outperforms GENRE in strict evaluation, but GENRE performs better in loose evaluation (accuracy@k).

The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging. One common evaluation approach uses multiple-choice questions to limit the response space. The model is then evaluated by ranking the candidate answers by the log probability of the first token prediction. However, first-tokens may not consistently reflect the final response output, due to model’s diverse response styles such as starting with “Sure” or refusing to answer. Consequently, first-token evaluation is not indicative of model behaviour when interacting with users. But by how much? We evaluate how aligned first-token evaluation is with the text output along several dimensions, namely final option choice, refusal rate, choice distribution and robustness under prompt perturbation. Our results show that the two approaches are severely misaligned on all dimensions, reaching mismatch rates over 60%. Models heavily fine-tuned on conversational or safety data are especially impacted. Crucially, models remain misaligned even when we increasingly constrain prompts, i.e., force them to start with an option letter or example template. Our findings i) underscore the importance of inspecting the text output as well and ii) caution against relying solely on first-token evaluation.

Recent advances in Large Language Models (LLMs) have sparked wide interest in validating and comprehending the human-like cognitive-behavioral traits LLMs may capture and convey. These cognitive-behavioral traits include typically Attitudes, Opinions, Values (AOVs). However, measuring AOVs embedded within LLMs remains opaque, and different evaluation methods may yield different results. This has led to a lack of clarity on how different studies are related to each other and how they can be interpreted. This paper aims to bridge this gap by providing a comprehensive overview of recent works on the evaluation of AOVs in LLMs. Moreover, we survey related approaches in different stages of the evaluation pipeline in these works. By doing so, we address the potential and challenges with respect to understanding the model, human-AI alignment, and downstream application in social sciences. Finally, we provide practical insights into evaluation methods, model enhancement, and interdisciplinary collaboration, thereby contributing to the evolving landscape of evaluating AOVs in LLMs.

Human label variation (HLV) is a valuable source of information that arises when multiple human annotators provide different labels for valid reasons. In Natural Language Inference (NLI) earlier approaches to capturing HLV involve either collecting annotations from many crowd workers to represent human judgment distribution (HJD) or use expert linguists to provide detailed explanations for their chosen labels. While the former method provides denser HJD information, obtaining it is resource-intensive. In contrast, the latter offers richer textual information but it is challenging to scale up to many human judges. Besides, large language models (LLMs) are increasingly used as evaluators (“LLM judges”) but with mixed results, and few works aim to study HJDs. This study proposes to exploit LLMs to approximate HJDs using a small number of expert labels and explanations. Our experiments show that a few explanations significantly improve LLMs’ ability to approximate HJDs with and without explicit labels, thereby providing a solution to scale up annotations for HJD. However, fine-tuning smaller soft-label aware models with the LLM-generated model judgment distributions (MJDs) presents partially inconsistent results: while similar in distance, their resulting fine-tuned models and visualized distributions differ substantially. We show the importance of complementing instance-level distance measures with a global-level shape metric and visualization to more effectively evaluate MJDs against human judgment distributions.

One of the major aspects contributing to the striking performance of large language models (LLMs) is the vast amount of factual knowledge accumulated during pre-training. Yet, many LLMs suffer from self-inconsistency, which raises doubts about their trustworthiness and reliability. This paper focuses on entity type ambiguity, analyzing the proficiency and consistency of state-of-the-art LLMs in applying factual knowledge when prompted with ambiguous entities. To do so, we propose an evaluation protocol that disentangles knowing from applying knowledge, and test state-of-the-art LLMs on 49 ambiguous entities. Our experiments reveal that LLMs struggle with choosing the correct entity reading, achieving an average accuracy of only 85%, and as low as 75% with underspecified prompts. The results also reveal systematic discrepancies in LLM behavior, showing that while the models may possess knowledge, they struggle to apply it consistently, exhibit biases toward preferred readings, and display self-inconsistencies. This highlights the need to address entity ambiguity in the future for more trustworthy LLMs.

Instruction tuning has become an integral part of training pipelines for Large Language Models (LLMs) and has been shown to yield strong performance gains. In an orthogonal line of research, Annotation Error Detection (AED) has emerged as a tool for detecting quality problems in gold standard labels. So far, however, the application of AED methods has been limited to classification tasks. It is an open question how well AED methods generalize to language generation settings, which are becoming more widespread via LLMs. In this paper, we present a first and novel benchmark for AED on instruction tuning data: Donkii.It comprises three instruction-tuning datasets enriched with error annotations by experts and semi-automatic methods. We also provide a novel taxonomy of error types for instruction-tuning data.We find that all three datasets contain clear errors, which sometimes propagate directly into instruction-tuned LLMs. We propose four AED baselines for the generative setting and evaluate them extensively on the newly introduced dataset. Our results show that the choice of the right AED method and model size is indeed crucial and derive practical recommendations for how to use AED methods to clean instruction-tuning data.

Annotation tools are the starting point for creating Natural Language Processing (NLP) datasets. There is a wide variety of tools available; setting up these tools is however a hindrance. We propose Eevee, an annotation tool focused on simplicity, efficiency, and ease of use. It can run directly in the browser (no setup required) and uses tab-separated files (as opposed to character offsets or task-specific formats) for annotation. It allows for annotation of multiple tasks on a single dataset and supports four task-types: sequence labeling, span labeling, text classification and seq2seq.

We introduce Universal NER (UNER), an open, community-driven project to develop gold-standard NER benchmarks in many languages. The overarching goal of UNER is to provide high-quality, cross-lingually consistent annotations to facilitate and standardize multilingual NER research. UNER v1 contains 19 datasets annotated with named entities in a cross-lingual consistent schema across 13 diverse languages. In this paper, we detail the dataset creation and composition of UNER; we also provide initial modeling baselines on both in-language and cross-lingual learning settings. We will release the data, code, and fitted models to the public.

With the aim of improving the state-of-the-art (SOTA) on a target task, a standard strategy in Natural Language Processing (NLP) research is to design a new model, or modify the existing SOTA, and then benchmark its performance on the target task. We argue in favor of enriching this chain of actions by a preliminary error-guided analysis: First, explore weaknesses by analyzing the hard cases where the existing model fails, and then target the improvement based on those. Interpretable evaluation has received little attention for structured prediction tasks. Therefore we propose the first in-depth analysis suite for Relation Classification (RC), and show its effectiveness through a case study. We propose a set of potentially influential attributes to focus on (e.g., entity distance, sentence length). Then, we bucket our datasets based on these attributes, and weight the importance of them through correlations. This allows us to identify highly challenging scenarios for the RC model. By exploiting the findings of our analysis, with a carefully targeted adjustment to our architecture, we effectively improve the performance over the baseline by >3 Micro-F1.

Mainstream cross-lingual task-oriented dialogue (ToD) systems leverage the transfer learning paradigm by training a joint model for intent recognition and slot-filling in English and applying it, zero-shot, to other languages. We address a gap in prior research, which often overlooked the transfer to lower-resource colloquial varieties due to limited test data. Inspired by prior work on English varieties, we craft and manually evaluate perturbation rules that transform German sentences into colloquial forms and use them to synthesize test sets in four ToD datasets. Our perturbation rules cover 18 distinct language phenomena, enabling us to explore the impact of each perturbation on slot and intent performance. Using these new datasets, we conduct an experimental evaluation across six different transformers. Here, we demonstrate that when applied to colloquial varieties, ToD systems maintain their intent recognition performance, losing 6% (4.62 percentage points) in accuracy on average. However, they exhibit a significant drop in slot detection, with a decrease of 31% (21 percentage points) in slot F₁ score. Our findings are further supported by a transfer experiment from Standard American English to synthetic Urban African American Vernacular English.

The labor market is changing rapidly, prompting increased interest in the automatic extraction of occupational skills from text. With the advent of English benchmark job description datasets, there is a need for systems that handle their diversity well. We tackle the complexity in occupational skill datasets tasks—combining and leveraging multiple datasets for skill extraction, to identify rarely observed skills within a dataset, and overcoming the scarcity of skills across datasets. In particular, we investigate the retrieval-augmentation of language models, employing an external datastore for retrieving similar skills in a dataset-unifying manner. Our proposed method, Nearest Neighbor Occupational Skill Extraction (NNOSE) effectively leverages multiple datasets by retrieving neighboring skills from other datasets in the datastore. This improves skill extraction without additional fine-tuning. Crucially, we observe a performance gain in predicting infrequent patterns, with substantial gains of up to 30% span-F1 in cross-dataset settings.

With the rise of increasingly powerful and user-facing NLP systems, there is growing interest in assessing whether they have a good _representation of uncertainty_ by evaluating the quality of their predictive distribution over outcomes. We identify two main perspectives that drive starkly different evaluation protocols. The first treats predictive probability as an indication of model confidence; the second as an indication of human label variation. We discuss their merits and limitations, and take the position that both are crucial for trustworthy and fair NLP systems, but that exploiting a single predictive distribution is limiting. We recommend tools and highlight exciting directions towards models with disentangled representations of uncertainty about predictions and uncertainty about human labels.

Recent years have brought significant advances to Natural Language Processing (NLP), which enabled fast progress in the field of computational job market analysis. Core tasks in this application domain are skill extraction and classification from job postings. Because of its quick growth and its interdisciplinary nature, there is no exhaustive assessment of this field. This survey aims to fill this gap by providing a comprehensive overview of deep learning methodologies, datasets, and terminologies specific to NLP-driven skill extraction. Our comprehensive cataloging of publicly available datasets addresses the lack of consolidated information on dataset creation and characteristics. Finally, the focus on terminology addresses the current lack of consistent definitions for important concepts, such as hard and soft skills, and terms relating to skill extraction and classification.

Climate change (CC) has attracted increasing attention in NLP in recent years. However, detecting the stance on CC in multimodal data is understudied and remains challenging due to a lack of reliable datasets. To improve the understanding of public opinions and communication strategies, this paper presents MultiClimate, the first open-source manually-annotated stance detection dataset with 100 CC-related YouTube videos and 4,209 frame-transcript pairs. We deploy state-of-the-art vision and language models, as well as multimodal models for MultiClimate stance detection. Results show that text-only BERT significantly outperforms image-only ResNet50 and ViT. Combining both modalities achieves state-of-the-art, 0.747/0.749 in accuracy/F1. Our 100M-sized fusion models also beat CLIP and BLIP, as well as the much larger 9B-sized multimodal IDEFICS and text-only Llama3 and Gemma2, indicating that multimodal stance detection remains challenging for large language models. Our code, dataset, as well as supplementary materials, are available at https://github.com/werywjw/MultiClimate.

In legal decisions, split votes (SV) occur when judges cannot reach a unanimous decision, posing a difficulty for lawyers who must navigate diverse legal arguments and opinions. In high-stakes domains, %as human-AI interaction systems become increasingly important, understanding the alignment of perceived difficulty between humans and AI systems is crucial to build trust. However, existing NLP calibration methods focus on a classifier’s awareness of predictive performance, measured against the human majority class, overlooking inherent human label variation (HLV). This paper explores split votes as naturally observable human disagreement and value pluralism. We collect judges’ vote distributions from the European Court of Human Rights (ECHR), and present SV-ECHR, a case outcome classification (COC) dataset with SV information. We build a taxonomy of disagreement with SV-specific subcategories. We further assess the alignment of perceived difficulty between models and humans, as well as confidence- and human-calibration of COC models. We observe limited alignment with the judge vote distribution. To our knowledge, this is the first systematic exploration of calibration to human judgements in legal NLP. Our study underscores the necessity for further research on measuring and enhancing model calibration considering HLV in legal decision tasks.

Human label variation arises when annotators assign different labels to the same item for valid reasons, while annotation errors occur when labels are assigned for invalid reasons. These two issues are prevalent in NLP benchmarks, yet existing research has studied them in isolation. To the best of our knowledge, there exists no prior work that focuses on teasing apart error from signal, especially in cases where signal is beyond black-and-white.To fill this gap, we introduce a systematic methodology and a new dataset, VariErr (variation versus error), focusing on the NLI task in English. We propose a 2-round annotation procedure with annotators explaining each label and subsequently judging the validity of label-explanation pairs.VariErr contains 7,732 validity judgments on 1,933 explanations for 500 re-annotated MNLI items. We assess the effectiveness of various automatic error detection (AED) methods and GPTs in uncovering errors versus human label variation. We find that state-of-the-art AED methods significantly underperform GPTs and humans. While GPT-4 is the best system, it still falls short of human performance. Our methodology is applicable beyond NLI, offering fertile ground for future research on error versus plausible variation, which in turn can yield better and more trustworthy NLP systems.

Deductive reasoning plays a pivotal role in the formulation of sound and cohesive arguments. It allows individuals to draw conclusions that logically follow, given the truth value of the information provided. Recent progress in the domain of large language models (LLMs) has showcased their capability in executing deductive reasoning tasks. Nonetheless, a significant portion of research primarily assesses the accuracy of LLMs in solving such tasks, often overlooking a deeper analysis of their reasoning behavior. In this study, we draw upon principles from cognitive psychology to examine inferential strategies employed by LLMs, through a detailed evaluation of their responses to propositional logic problems. Our findings indicate that LLMs display reasoning patterns akin to those observed in humans, including strategies like supposition following or chain construction. Moreover, our research demonstrates that the architecture and scale of the model significantly affect its preferred method of reasoning, with more advanced models tending to adopt strategies more frequently than less sophisticated ones. Importantly, we assert that a model’s accuracy, that is the correctness of its final conclusion, does not necessarily reflect the validity of its reasoning process. This distinction underscores the necessity for more nuanced evaluation procedures in the field.

Natural language processing (NLP) has largely focused on modelling standardized languages. More recently, attention has increasingly shifted to local, non-standardized languages and dialects. However, the relevant speaker populations’ needs and wishes with respect to NLP tools are largely unknown. In this paper, we focus on dialects and regional languages related to German – a group of varieties that is heterogeneous in terms of prestige and standardization. We survey speakers of these varieties (N=327) and present their opinions on hypothetical language technologies for their dialects. Although attitudes vary among subgroups of our respondents, we find that respondents are especially in favour of potential NLP tools that work with dialectal input (especially audio input) such as virtual assistants, and less so for applications that produce dialectal output such as machine translation or spellcheckers.

Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific, so combining datasets to obtain better performance is non-trivial. We explore a multi-domain training setup for RC, and attempt to improve performance by encoding domain information. Our proposed models improve > 2 Macro-F1 against the baseline setup, and our analysis reveals that not all the labels benefit the same: The classes which occupy a similar space across domains (i.e., their interpretation is close across them, for example “physical”) benefit the least, while domain-dependent relations (e.g., “part-of”) improve the most when encoding domain information.

Polar questions are common in dialogue and expect exactly one of two answers (yes/no). It is however not uncommon for speakers to bypass these expected choices and answer, for example, “Islands are generally by the sea” to the question: “An island? By the sea?”. While such answers are natural in spoken dialogues, conversational systems still struggle to interpret them. Seminal work to interpret indirect answers were made in recent years—but only for English and with strict question formulations. In this work, we present a new corpus for French and Spanish—IndirectQA —where we mine subtitle data for indirect answers to study the labeling task with six different labels, while broadening polar questions to include also implicit polar questions (statements that trigger a yes/no-answer which are not necessarily formulated as a question). We opted for subtitles since they are a readily available source of conversation in various languages, but also come with peculiarities and challenges which we will discuss. Overall, we provide the first results on French and Spanish. They show that the task is challenging: the baseline accuracy scores drop from 61.43 on English to 44.06 for French and Spanish.

Despite the success of the Universal Dependencies (UD) project exemplified by its impressive language breadth, there is still a lack in ‘within-language breadth’: most treebanks focus on standard languages. Even for German, the language with the most annotations in UD, so far no treebank exists for one of its language varieties spoken by over 10M people: Bavarian. To contribute to closing this gap, we present the first multi-dialect Bavarian treebank (MaiBaam) manually annotated with part-of-speech and syntactic dependency information in UD, covering multiple text genres (wiki, fiction, grammar examples, social, non-fiction). We highlight the morphosyntactic differences between the closely-related Bavarian and German and showcase the rich variability of speakers’ orthographies. Our corpus includes 15k tokens, covering dialects from all Bavarian-speaking areas spanning three countries. We provide baseline parsing and POS tagging results, which are lower than results obtained on German and vary substantially between different graph-based parsers. To support further research on Bavarian syntax, we make our dataset, language-specific guidelines and code publicly available.

Named Entity Recognition (NER) is a fundamental task to extract key information from texts, but annotated resources are scarce for dialects. This paper introduces the first dialectal NER dataset for German, BarNER, with 161K tokens annotated on Bavarian Wikipedia articles (bar-wiki) and tweets (bar-tweet), using a schema adapted from German CoNLL 2006 and GermEval. The Bavarian dialect differs from standard German in lexical distribution, syntactic construction, and entity information. We conduct in-domain, cross-domain, sequential, and joint experiments on two Bavarian and three German corpora and present the first comprehensive NER results on Bavarian. Incorporating knowledge from the larger German NER (sub-)datasets notably improves on bar-wiki and moderately on bar-tweet. Inversely, training first on Bavarian contributes slightly to the seminal German CoNLL 2006 corpus. Moreover, with gold dialect labels on Bavarian tweets, we assess multi-task learning between five NER and two Bavarian-German dialect identification tasks and achieve NER SOTA on bar-wiki. We substantiate the necessity of our low-resource BarNER corpus and the importance of diversity in dialects, genres, and topics in enhancing model performance.

Digital assistants perform well in high-resource languages like English, where tasks like slot and intent detection (SID) are well-supported. Many recent SID datasets start including multiple language varieties. However, it is unclear how realistic these translated datasets are. Therefore, we extend one such dataset, namely xSID-0.4, to include two underrepresented languages: Bavarian, a German dialect, and Lithuanian, a Baltic language. Both language variants have limited speaker populations and are often not included in multilingual projects. In addition to translations we provide “natural” queries to digital assistants generated by native speakers. We further include utterances from another dataset for Bavarian to build the richest SID dataset available today for a low-resource dialect without standard orthography. We then set out to evaluate models trained on English in a zero-shot scenario on our target language variants. Our evaluation reveals that translated data can produce overly optimistic scores. However, the error patterns in translated and natural datasets are highly similar. Cross-dataset experiments demonstrate that data collection methods influence performance, with scores lower than those achieved with single-dataset translations. This work contributes to enhancing SID datasets for underrepresented languages, yielding NaLiBaSID, a new evaluation dataset for Bavarian and Lithuanian.

This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR), on Track C: Cross-lingual. The task aims to detect semantic relatedness of two sentences from the same languages. For cross-lingual approach we developed a set of linguistics-inspired models trained with several task-specific strategies. We 1) utilize language vectors for selection of donor languages; 2) investigate the multi-source approach for training; 3) use transliteration of non-latin script to study impact of “script gap”; 4) opt machine translation for data augmentation. We additionally compare the performance of XLM-RoBERTa and Furina with the same training strategy. Our submission achieved the first place in the C8 (Kinyarwanda) test.

NLP datasets annotated with human judgments are rife with disagreements between the judges. This is especially true for tasks depending on subjective judgments such as sentiment analysis or offensive language detection. Particularly in these latter cases, the NLP community has come to realize that the common approach of reconciling’ these different subjective interpretations risks misrepresenting the evidence. Many NLP researchers have therefore concluded that rather than eliminating disagreements from annotated corpora, we should preserve themindeed, some argue that corpora should aim to preserve all interpretations produced by annotators. But this approach to corpus creation for NLP has not yet been widely accepted. The objective of the Le-Wi-Di series of shared tasks is to promote this approach to developing NLP models by providing a unified framework for training and evaluating with such datasets. We report on the second such shared task, which differs from the first edition in three crucial respects: (i) it focuses entirely on NLP, instead of both NLP and computer vision tasks in its first edition; (ii) it focuses on subjective tasks, instead of covering different types of disagreements as training with aggregated labels for subjective NLP tasks is in effect a misrepresentation of the data; and (iii) for the evaluation, we concentrated on soft approaches to evaluation. This second edition of Le-Wi-Di attracted a wide array of partici- pants resulting in 13 shared task submission papers.

The increasing number of benchmarks for Natural Language Processing (NLP) tasks in the computational job market domain highlights the demand for methods that can handle job-related tasks such as skill extraction, skill classification, job title classification, and de-identification. While some approaches have been developed that are specific to the job market domain, there is a lack of generalized, multilingual models and benchmarks for these tasks. In this study, we introduce a language model called ESCOXLM-R, based on XLM-R-large, which uses domain-adaptive pre-training on the European Skills, Competences, Qualifications and Occupations (ESCO) taxonomy, covering 27 languages. The pre-training objectives for ESCOXLM-R include dynamic masked language modeling and a novel additional objective for inducing multilingual taxonomical ESCO relations. We comprehensively evaluate the performance of ESCOXLM-R on 6 sequence labeling and 3 classification tasks in 4 languages and find that it achieves state-of-the-art results on 6 out of 9 datasets. Our analysis reveals that ESCOXLM-R performs better on short spans and outperforms XLM-R-large on entity-level and surface-level span-F1, likely due to ESCO containing short skill and occupation titles, and encoding information on the entity-level.

Recently, various intermediate layer distillation (ILD) objectives have been shown to improve compression of BERT models via Knowledge Distillation (KD). However, a comprehensive evaluation of the objectives in both task-specific and task-agnostic settings is lacking. To the best of our knowledge, this is the first work comprehensively evaluating distillation objectives in both settings. We show that attention transfer gives the best performance overall. We also study the impact of layer choice when initializing the student from the teacher layers, finding a significant impact on the performance in task-specific distillation. For vanilla KD and hidden states transfer, initialisation with lower layers of the teacher gives a considerable improvement over higher layers, especially on the task of QNLI (up to an absolute percentage change of 17.8 in accuracy). Attention transfer behaves consistently under different initialisation settings. We release our code as an efficient transformer-based model distillation framework for further studies.

Transferring information retrieval (IR) models from a high-resource language (typically English) to other languages in a zero-shot fashion has become a widely adopted approach. In this work, we show that the effectiveness of zero-shot rankers diminishes when queries and documents are present in different languages. Motivated by this, we propose to train ranking models on artificially code-switched data instead, which we generate by utilizing bilingual lexicons. To this end, we experiment with lexicons induced from (1) cross-lingual word embeddings and (2) parallel Wikipedia page titles. We use the mMARCO dataset to extensively evaluate reranking models on 36 language pairs spanning Monolingual IR (MoIR), Cross-lingual IR (CLIR), and Multilingual IR (MLIR). Our results show that code-switching can yield consistent and substantial gains of 5.1 MRR@10 in CLIR and 3.9 MRR@10 in MLIR, while maintaining stable performance in MoIR. Encouragingly, the gains are especially pronounced for distant languages (up to 2x absolute gain). We further show that our approach is robust towards the ratio of code-switched tokens and also extends to unseen languages. Our results demonstrate that training on code-switched data is a cheap and effective way of generalizing zero-shot rankers for cross-lingual and multilingual retrieval.

Relation Extraction (RE) remains a challenging task, especially when considering realistic out-of-domain evaluations. One of the main reasons for this is the limited training size of current RE datasets: obtaining high-quality (manually annotated) data is extremely expensive and cannot realistically be repeated for each new domain. An intermediate training step on data from related tasks has shown to be beneficial across many NLP tasks. However, this setup still requires supplementary annotated data, which is often not available. In this paper, we investigate intermediate pre-training specifically for RE. We exploit the affinity between syntactic structure and semantic RE, and identify the syntactic relations which are closely related to RE by being on the shortest dependency path between two entities. We then take advantage of the high accuracy of current syntactic parsers in order to automatically obtain large amounts of low-cost pre-training data. By pre-training our RE model on the relevant syntactic relations, we are able to outperform the baseline in five out of six cross-domain setups, without any additional annotated data.

Manually annotated datasets are crucial for training and evaluating Natural Language Processing models. However, recent work has discovered that even widely-used benchmark datasets contain a substantial number of erroneous annotations. This problem has been addressed with Annotation Error Detection (AED) models, which can flag such errors for human re-annotation. However, even though many of these AED methods assume a final curation step in which a human annotator decides whether the annotation is erroneous, they have been developed as static models without any human-in-the-loop component. In this work, we propose ActiveAED, an AED method that can detect errors more accurately by repeatedly querying a human for error corrections in its prediction loop. We evaluate ActiveAED on eight datasets spanning five different tasks and find that it leads to improvements over the state of the art on seven of them, with gains of up to six percentage points in average precision.

Representational spaces learned via language modeling are fundamental to Natural Language Processing (NLP), however there has been limited understanding regarding how and when during training various types of linguistic information emerge and interact. Leveraging a novel information theoretic probing suite, which enables direct comparisons of not just task performance, but their representational subspaces, we analyze nine tasks covering syntax, semantics and reasoning, across 2M pre-training steps and five seeds. We identify critical learning phases across tasks and time, during which subspaces emerge, share information, and later disentangle to specialize. Across these phases, syntactic knowledge is acquired rapidly after 0.5% of full training. Continued performance improvements primarily stem from the acquisition of open-domain knowledge, while semantics and reasoning tasks benefit from later boosts to long-range contextualization and higher specialization. Measuring cross-task similarity further reveals that linguistically related tasks share information throughout training, and do so more during the critical phase of learning than before or after. Our findings have implications for model interpretability, multi-task learning, and learning from limited data.

Language understanding is a multi-faceted cognitive capability, which the Natural Language Processing (NLP) community has striven to model computationally for decades. Traditionally, facets of linguistic intelligence have been compartmentalized into tasks with specialized model architectures and corresponding evaluation protocols. With the advent of large language models (LLMs) the community has witnessed a dramatic shift towards general purpose, task-agnostic approaches powered by generative models. As a consequence, the traditional compartmentalized notion of language tasks is breaking down, followed by an increasing challenge for evaluation and analysis. At the same time, LLMs are being deployed in more real-world scenarios, including previously unforeseen zero-shot setups, increasing the need for trustworthy and reliable systems. Therefore, we argue that it is time to rethink what constitutes tasks and model evaluation in NLP, and pursue a more holistic view on language, placing trustworthiness at the center. Towards this goal, we review existing compartmentalized approaches for understanding the origins of a model’s functional capacity, and provide recommendations for more multi-faceted evaluation protocols.

Label aggregation such as majority voting is commonly used to resolve annotator disagreement in dataset creation. However, this may disregard minority values and opinions. Recent studies indicate that learning from individual annotations outperforms learning from aggregated labels, though they require a considerable amount of annotation. Active learning, as an annotation cost-saving strategy, has not been fully explored in the context of learning from disagreement. We show that in the active learning setting, a multi-head model performs significantly better than a single-head model in terms of uncertainty estimation. By designing and evaluating acquisition functions with annotator-specific heads on two datasets, we show that group-level entropy works generally well on both datasets. Importantly, it achieves performance in terms of both prediction and uncertainty estimation comparable to full-scale training from disagreement, while saving 70% of the annotation budget.

In legal NLP, Case Outcome Classification (COC) must not only be accurate but also trustworthy and explainable. Existing work in explainable COC has been limited to annotations by a single expert. However, it is well-known that lawyers may disagree in their assessment of case facts. We hence collect a novel dataset RaVE: Rationale Variation in ECHR, which is obtained from two experts in the domain of international human rights law, for whom we observe weak agreement. We study their disagreements and build a two-level task-independent taxonomy, supplemented with COC-specific subcategories. To our knowledge, this is the first work in the legal NLP that focuses on human label variation. We quantitatively assess different taxonomy categories and find that disagreements mainly stem from underspecification of the legal context, which poses challenges given the typically limited granularity and noise in COC metadata. We further assess the explainablility of state-of-the-art COC models on RaVE and observe limited agreement between models and experts. Overall, our case study reveals hitherto underappreciated complexities in creating benchmark datasets in legal NLP that revolve around identifying aspects of a case’s facts supposedly relevant for its outcome.

In Natural Language Generation (NLG) tasks, for any input, multiple communicative goals are plausible, and any goal can be put into words, or produced, in multiple ways. We characterise the extent to which human production varies lexically, syntactically, and semantically across four NLG tasks, connecting human production variability to aleatoric or data uncertainty. We then inspect the space of output strings shaped by a generation system’s predicted probability distribution and decoding algorithm to probe its uncertainty. For each test input, we measure the generator’s calibration to human production variability. Following this instance-level approach, we analyse NLG models and decoding strategies, demonstrating that probing a generator with multiple samples and, when possible, multiple references, provides the level of detail necessary to gain understanding of a model’s representation of uncertainty.

One of the challenges with finetuning pretrained language models (PLMs) is that their tokenizer is optimized for the language(s) it was pretrained on, but brittle when it comes to previously unseen variations in the data. This can for instance be observed when finetuning PLMs on one language and evaluating them on data in a closely related language variety with no standardized orthography. Despite the high linguistic similarity, tokenization no longer corresponds to meaningful representations of the target data, leading to low performance in, e.g., part-of-speech tagging. In this work, we finetune PLMs on seven languages from three different families and analyze their zero-shot performance on closely related, non-standardized varieties. We consider different measures for the divergence in the tokenization of the source and target data, and the way they can be adjusted by manipulating the tokenization during the finetuning step. Overall, we find that the similarity between the percentage of words that get split into subwords in the source and target data (the split word ratio difference) is the strongest predictor for model performance on target data.

This report presents the results of the shared tasks organized as part of the VarDial Evaluation Campaign 2023. The campaign is part of the tenth workshop on Natural Language Processing (NLP) for Similar Languages, Varieties and Dialects (VarDial), co-located with EACL 2023. Three separate shared tasks were included this year: Slot and intent detection for low-resource language varieties (SID4LR), Discriminating Between Similar Languages – True Labels (DSL-TL), and Discriminating Between Similar Languages – Speech (DSL-S). All three tasks were organized for the first time this year.

Most research in Relation Extraction (RE) involves the English language, mainly due to the lack of multi-lingual resources. We propose Multi-CrossRE, the broadest multi-lingual dataset for RE, including 26 languages in addition to English, and covering six text domains. Multi-CrossRE is a machine translated version of CrossRE (Bassignana and Plank, 2022), with a sub-portion including more than 200 sentences in seven diverse languages checked by native speakers. We run a baseline model over the 26 new datasets and–as sanity check–over the 26 back-translations to English. Results on the back-translated data are consistent with the ones on the original English CrossRE, indicating high quality of the translation and the resulting dataset.

Bilingual word lexicons map words in one language to their synonyms in another language. Numerous papers have explored bilingual lexicon induction (BLI) in high-resource scenarios, framing a typical pipeline that consists of two steps: (i) unsupervised bitext mining and (ii) unsupervised word alignment. At the core of those steps are pre-trained large language models (LLMs).In this paper we present the analysis of the BLI pipeline for German and two of its dialects, Bavarian and Alemannic. This setup poses a number of unique challenges, attributed to the scarceness of resources, relatedness of the languages and lack of standardization in the orthography of dialects. We analyze the BLI outputs with respect to word frequency and the pairwise edit distance. Finally, we release an evaluation dataset consisting of manual annotations for 1K bilingual word pairs labeled according to their semantic similarity.

Despite much progress in recent years, the vast majority of work in natural language processing (NLP) is on standard languages with many speakers. In this work, we instead focus on low-resource languages and in particular non-standardized low-resource languages. Even within branches of major language families, often considered well-researched, little is known about the extent and type of available resources and what the major NLP challenges are for these language varieties. The first step to address this situation is a systematic survey of available corpora (most importantly, annotated corpora, which are particularly valuable for NLP research). Focusing on Germanic low-resource language varieties, we provide such a survey in this paper. Except for geolocation (origin of speaker or document), we find that manually annotated linguistic resources are sparse and, if they exist, mostly cover morphosyntax. Despite this lack of resources, we observe that interest in this area is increasing: there is active development and a growing research community. To facilitate research, we make our overview of over 80 corpora publicly available.

Cross-lingual transfer of parsing models has been shown to work well for several closely-related languages, but predicting the success in other cases remains hard. Our study is a comprehensive analysis of the impact of linguistic distance on the transfer of UD parsers. As an alternative to syntactic typological distances extracted from URIEL, we propose three text-based feature spaces and show that they can be more precise predictors, especially on a more local scale, when only shorter distances are taken into account. Our analyses also reveal that the good coverage in typological databases is not among the factors that explain good transfer.

Making an informed choice of pre-trained language model (LM) is critical for performance, yet environmentally costly, and as such widely underexplored. The field of Computer Vision has begun to tackle encoder ranking, with promising forays into Natural Language Processing, however they lack coverage of linguistic tasks such as structured prediction. We propose probing to rank LMs, specifically for parsing dependencies in a given language, by measuring the degree to which labeled trees are recoverable from an LM’s contextualized embeddings. Across 46 typologically and architecturally diverse LM-language pairs, our probing approach predicts the best LM choice 79% of the time using orders of magnitude less compute than training a full parser. Within this study, we identify and analyze one recently proposed decoupled LM—RemBERT—and find it strikingly contains less inherent dependency information, but often yields the best parser after full fine-tuning. Without this outlier our approach identifies the best LM in 89% of cases.

Skill Extraction (SE) is an important and widely-studied task useful to gain insights into labor market dynamics. However, there is a lacuna of datasets and annotation guidelines; available datasets are few and contain crowd-sourced labels on the span-level or labels from a predefined skill inventory. To address this gap, we introduce SKILLSPAN, a novel SE dataset consisting of 14.5K sentences and over 12.5K annotated spans. We release its respective guidelines created over three different sources annotated for hard and soft skills by domain experts. We introduce a BERT baseline (Devlin et al., 2019). To improve upon this baseline, we experiment with language models that are optimized for long spans (Joshi et al., 2020; Beltagy et al., 2020), continuous pre-training on the job posting domain (Han and Eisenstein, 2019; Gururangan et al., 2020), and multi-task learning (Caruana, 1997). Our results show that the domain-adapted models significantly outperform their non-adapted counterparts, and single-task outperforms multi-task learning.

Probing has become an important tool for analyzing representations in Natural Language Processing (NLP). For graphical NLP tasks such as dependency parsing, linear probes are currently limited to extracting undirected or unlabeled parse trees which do not capture the full task. This work introduces DepProbe, a linear probe which can extract labeled and directed dependency parse trees from embeddings while using fewer parameters and compute than prior methods. Leveraging its full task coverage and lightweight parametrization, we investigate its predictive power for selecting the best transfer language for training a full biaffine attention parser. Across 13 languages, our proposed method identifies the best source treebank 94% of the time, outperforming competitive baselines and prior work. Finally, we analyze the informativeness of task-specific subspaces in contextual embeddings as well as which benefits a full parser’s non-linear parametrization provides.

Over the last five years, research on Relation Extraction (RE) witnessed extensive progress with many new dataset releases. At the same time, setup clarity has decreased, contributing to increased difficulty of reliable empirical evaluation (Taillé et al., 2020). In this paper, we provide a comprehensive survey of RE datasets, and revisit the task definition and its adoption by the community. We find that cross-dataset and cross-domain setups are particularly lacking. We present an empirical study on scientific Relation Classification across two datasets. Despite large data overlap, our analysis reveals substantial discrepancies in annotation. Annotation discrepancies strongly impact Relation Classification performance, explaining large drops in cross-dataset evaluations. Variation within further sub-domains exists but impacts Relation Classification only to limited degrees. Overall, our study calls for more rigour in reporting setups in RE and evaluation across multiple test sets.

Calibration is a popular framework to evaluate whether a classifier knows when it does not know - i.e., its predictive probabilities are a good indication of how likely a prediction is to be correct. Correctness is commonly estimated against the human majority class. Recently, calibration to human majority has been measured on tasks where humans inherently disagree about which class applies. We show that measuring calibration to human majority given inherent disagreements is theoretically problematic, demonstrate this empirically on the ChaosNLI dataset, and derive several instance-level measures of calibration that capture key statistical properties of human judgements - including class frequency, ranking and entropy.

With the increase in availability of large pre-trained language models (LMs) in Natural Language Processing (NLP), it becomes critical to assess their fit for a specific target task a priori—as fine-tuning the entire space of available LMs is computationally prohibitive and unsustainable. However, encoder transferability estimation has received little to no attention in NLP. In this paper, we propose to generate quantitative evidence to predict which LM, out of a pool of models, will perform best on a target task without having to fine-tune all candidates. We provide a comprehensive study on LM ranking for 10 NLP tasks spanning the two fundamental problem types of classification and structured prediction. We adopt the state-of-the-art Logarithm of Maximum Evidence (LogME) measure from Computer Vision (CV) and find that it positively correlates with final LM performance in 94% of the setups.In the first study of its kind, we further compare transferability measures with the de facto standard of human practitioner ranking, finding that evidence from quantitative metrics is more robust than pure intuition and can help identify unexpected LM candidates.

Linguistic information is encoded at varying timescales (subwords, phrases, etc.) and communicative levels, such as syntax and semantics. Contextualized embeddings have analogously been found to capture these phenomena at distinctive layers and frequencies. Leveraging these findings, we develop a fully learnable frequency filter to identify spectral profiles for any given task. It enables vastly more granular analyses than prior handcrafted filters, and improves on efficiency. After demonstrating the informativeness of spectral probing over manual filters in a monolingual setting, we investigate its multilingual characteristics across seven diverse NLP tasks in six languages. Our analyses identify distinctive spectral profiles which quantify cross-task similarity in a linguistically intuitive manner, while remaining consistent across languages—highlighting their potential as robust, lightweight task descriptors.

Human variation in labeling is often considered noise. Annotation projects for machine learning (ML) aim at minimizing human label variation, with the assumption to maximize data quality and in turn optimize and maximize machine learning metrics. However, thisconventional practice assumes that there exists a *ground truth*, and neglects that there exists genuine human variation in labeling due to disagreement, subjectivity in annotation or multiple plausible answers.In this position paper, we argue that this big open problem of human label variation persists and critically needs more attention to move our field forward. This is because human label variation impacts all stages of the ML pipeline: *data, modeling and evaluation*. However, few works consider all of these dimensions jointly; and existing research is fragmented. We reconcile different previously proposed notions of human label variation, provide a repository of publicly-available datasets with un-aggregated labels, depict approaches proposed so far, identify gaps and suggest ways forward. As datasets are becoming increasingly available, we hope that this synthesized view on the “problem” will lead to an open discussion on possible strategies to devise fundamentally new directions.

The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well. Yet, compared to more established disciplines, a lack of common experimental standards remains an open challenge to the field at large. Starting from fundamental scientific principles, we distill ongoing discussions on experimental standards in NLP into a single, widely-applicable methodology. Following these best practices is crucial to strengthen experimental evidence, improve reproducibility and enable scientific progress. These standards are further collected in a public repository to help them transparently adapt to future needs.

Relation Extraction (RE) has attracted increasing attention, but current RE evaluation is limited to in-domain evaluation setups. Little is known on how well a RE system fares in challenging, but realistic out-of-distribution evaluation setups. To address this gap, we propose CrossRE, a new, freely-available cross-domain benchmark for RE, which comprises six distinct text domains and includes multi-label annotations. An additional innovation is that we release meta-data collected during annotation, to include explanations and flags of difficult instances. We provide an empirical evaluation with a state-of-the-art model for relation classification. As the meta-data enables us to shed new light on the state-of-the-art model, we provide a comprehensive analysis on the impact of difficult cases and find correlations between model and human annotations. Overall, our empirical investigation highlights the difficulty of cross-domain RE. We release our dataset, to spur more research in this direction.

Skill Classification (SC) is the task of classifying job competences from job postings. This work is the first in SC applied to Danish job vacancy data. We release the first Danish job posting dataset: *Kompetencer* (_en_: competences), annotated for nested spans of competences. To improve upon coarse-grained annotations, we make use of The European Skills, Competences, Qualifications and Occupations (ESCO; le Vrang et al., (2014)) taxonomy API to obtain fine-grained labels via distant supervision. We study two setups: The zero-shot and few-shot classification setting. We fine-tune English-based models and RemBERT (Chung et al., 2020) and compare them to in-language Danish models. Our results show RemBERT significantly outperforms all other models in both the zero-shot and the few-shot setting.

As input representation for each sub-word, the original BERT architecture proposes the sum of the sub-word embedding, position embedding and a segment embedding. Sub-word and position embeddings are well-known and studied, and encode lexical information and word position, respectively. In contrast, segment embeddings are less known and have so far received no attention, despite being ubiquitous in large pre-trained language models. The key idea of segment embeddings is to encode to which of the two sentences (segments) a word belongs to — the intuition is to inform the model about the separation of sentences for the next sentence prediction pre-training task. However, little is known on whether the choice of segment impacts performance. In this work, we try to fill this gap and empirically study the impact of the segment embedding during inference time for a variety of pre-trained embeddings and target tasks. We hypothesize that for single-sentence prediction tasks performance is not affected — neither in mono- nor multilingual setups — while it matters when swapping segment IDs in paired-sentence tasks. To our surprise, this is not the case. Although for classification tasks and monolingual BERT models no large differences are observed, particularly word-level multilingual prediction tasks are heavily impacted. For low-resource syntactic tasks, we observe impacts of segment embedding and multilingual BERT choice. We find that the default setting for the most used multilingual BERT model underperforms heavily, and a simple swap of the segment embeddings yields an average improvement of 2.5 points absolute LAS score for dependency parsing over 9 different treebanks.

Fine-tuning general-purpose pre-trained models has become a de-facto standard, also for Vision and Language tasks such as Visual Question Answering (VQA). In this paper, we take a step back and ask whether a fine-tuned model has superior linguistic and reasoning capabilities than a prior state-of-the-art architecture trained from scratch on the training data alone. We perform a fine-grained evaluation on out-of-distribution data, including an analysis on robustness due to linguistic variation (rephrasings). Our empirical results confirm the benefit of pre-training on overall performance and rephrasing in particular. But our results also uncover surprising limitations, particularly for answering questions involving boolean operations. To complement the empirical evaluation, this paper also surveys relevant earlier work on 1) available VQA data sets, 2) models developed for VQA, 3) pre-trained Vision+Language models, and 4) earlier fine-grained evaluation of pre-trained Vision+Language models.

Massively multilingual language models (MMLMs) have become a widely-used representation method, and multiple large MMLMs were proposed in recent years. A trend is to train MMLMs on larger text corpora or with more layers. In this paper we set out to test recent popular MMLMs on detecting semantically ambiguous and complex named entities with an academic GPU budget. Our submission of a single model for 11 languages on the SemEval Task 11 MultiCoNER shows that a vanilla transformer-CRF with XLM-R_large outperforms the more recent RemBERT, ranking 9th from 26 submissions in the multilingual track. Compared to RemBERT, the XLM-R model has the additional advantage to fit on a slice of a multi-instance GPU. As contrary to expectations and recent findings, we found RemBERT to not be the best MMLM, we further set out to investigate this discrepancy with additional experiments on multilingual Wikipedia NER data. While we expected RemBERT to have an edge on that dataset as it is closer to its pre-training data, surprisingly, our results show that this is not the case, suggesting that text domain match does not explain the discrepancy.

Disagreement between coders is ubiquitous in virtually all datasets annotated with human judgements in both natural language processing and computer vision. However, most supervised machine learning methods assume that a single preferred interpretation exists for each item, which is at best an idealization. The aim of the SemEval-2021 shared task on learning with disagreements (Le-Wi-Di) was to provide a unified testing framework for methods for learning from data containing multiple and possibly contradictory annotations covering the best-known datasets containing information about disagreements for interpreting language and classifying images. In this paper we describe the shared task and its results.

De-identification is the task of detecting privacy-related entities in text, such as person names, emails and contact data. It has been well-studied within the medical domain. The need for de-identification technology is increasing, as privacy-preserving data handling is in high demand in many domains. In this paper, we focus on job postings. We present JobStack, a new corpus for de-identification of personal data in job vacancies on Stackoverflow. We introduce baselines, comparing Long-Short Term Memory (LSTM) and Transformer models. To improve these baselines, we experiment with BERT representations, and distantly related auxiliary data via multi-task learning. Our results show that auxiliary data helps to improve de-identification performance. While BERT representations improve performance, surprisingly “vanilla” BERT turned out to be more effective than BERT trained on Stackoverflow-related data.

Finding informative COVID-19 posts in a stream of tweets is very useful to monitor health-related updates. Prior work focused on a balanced data setup and on English, but informative tweets are rare, and English is only one of the many languages spoken in the world. In this work, we introduce a new dataset of 5,000 tweets for finding informative COVID-19 tweets for Danish. In contrast to prior work, which balances the label distribution, we model the problem by keeping its natural distribution. We examine how well a simple probabilistic model and a convolutional neural network (CNN) perform on this task. We find a weighted CNN to work well but it is sensitive to embedding and hyperparameter choices. We hope the contributed dataset is a starting point for further work in this direction.

Lexical normalization is the task of transforming an utterance into its standardized form. This task is beneficial for downstream analysis, as it provides a way to harmonize (often spontaneous) linguistic variation. Such variation is typical for social media on which information is shared in a multitude of ways, including diverse languages and code-switching. Since the seminal work of Han and Baldwin (2011) a decade ago, lexical normalization has attracted attention in English and multiple other languages. However, there exists a lack of a common benchmark for comparison of systems across languages with a homogeneous data and evaluation setup. The MultiLexNorm shared task sets out to fill this gap. We provide the largest publicly available multilingual lexical normalization benchmark including 13 language variants. We propose a homogenized evaluation setup with both intrinsic and extrinsic evaluation. As extrinsic evaluation, we use dependency parsing and part-of-speech tagging with adapted evaluation metrics (a-LAS, a-UAS, and a-POS) to account for alignment discrepancies. The shared task hosted at W-NUT 2021 attracted 9 participants and 18 submissions. The results show that neural normalization systems outperform the previous state-of-the-art system by a large margin. Downstream parsing and part-of-speech tagging performance is positively affected but to varying degrees, with improvements of up to 1.72 a-LAS, 0.85 a-UAS, and 1.54 a-POS for the winning system.

The lack of publicly available evaluation data for low-resource languages limits progress in Spoken Language Understanding (SLU). As key tasks like intent classification and slot filling require abundant training data, it is desirable to reuse existing data in high-resource languages to develop models for low-resource scenarios. We introduce xSID, a new benchmark for cross-lingual (x) Slot and Intent Detection in 13 languages from 6 language families, including a very low-resource dialect. To tackle the challenge, we propose a joint learning approach, with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer. We study two setups which differ by type and language coverage of the pre-trained embeddings. Our results show that jointly learning the main tasks with masked language modeling is effective for slots, while machine translation transfer works best for intent classification.

Supervised learning assumes that a ground truth label exists. However, the reliability of this ground truth depends on human annotators, who often disagree. Prior work has shown that this disagreement can be helpful in training models. We propose a novel method to incorporate this disagreement as information: in addition to the standard error computation, we use soft-labels (i.e., probability distributions over the annotator labels) as an auxiliary task in a multi-task neural network. We measure the divergence between the predictions and the target soft-labels with several loss-functions and evaluate the models on various NLP tasks. We find that the soft-label prediction auxiliary task reduces the penalty for errors on ambiguous entities, and thereby mitigates overfitting. It significantly improves performance across tasks, beyond the standard approach and prior work.

Indirect answers are replies to polar questions without the direct use of word cues such as ‘yes’ and ‘no’. Humans are very good at understanding indirect answers, such as ‘I gotta go home sometime’, when asked ‘You wanna crash on the couch?’. Understanding indirect answers is a challenging problem for dialogue systems. In this paper, we introduce a new English corpus to study the problem of understanding indirect answers. Instead of crowd-sourcing both polar questions and answers, we collect questions and indirect answers from transcripts of a prominent TV series and manually annotate them for answer type. The resulting dataset contains 5,930 question-answer pairs. We release both aggregated and raw human annotations. We present a set of experiments in which we evaluate Convolutional Neural Networks (CNNs) for this task, including a cross-dataset evaluation and experiments with learning from disagreements in annotation. Our results show that the task of interpreting indirect answers remains challenging, yet we obtain encouraging improvements when explicitly modeling human disagreement.

Transfer learning, particularly approaches that combine multi-task learning with pre-trained contextualized embeddings and fine-tuning, have advanced the field of Natural Language Processing tremendously in recent years. In this paper we present MaChAmp, a toolkit for easy fine-tuning of contextualized embeddings in multi-task settings. The benefits of MaChAmp are its flexible configuration options, and the support of a variety of natural language processing tasks in a uniform toolkit, from text classification and sequence labeling to dependency parsing, masked language modeling, and text generation.

Deep neural networks have revolutionized many fields, including Natural Language Processing. This paper outlines teaching materials for an introductory lecture on deep learning in Natural Language Processing (NLP). The main submitted material covers a summer school lecture on encoder-decoder models. Complementary to this is a set of jupyter notebook slides from earlier teaching, on which parts of the lecture were based on. The main goal of this teaching material is to provide an overview of neural network approaches to natural language processing, while linking modern concepts back to the roots showing traditional essential counterparts. The lecture departs from count-based statistical methods and spans up to gated recurrent networks and attention, which is ubiquitous in today’s NLP.

Recent complementary strands of research have shown that leveraging information on the data source through encoding their properties into embeddings can lead to performance increase when training a single model on heterogeneous data sources. However, it remains unclear in which situations these dataset embeddings are most effective, because they are used in a large variety of settings, languages and tasks. Furthermore, it is usually assumed that gold information on the data source is available, and that the test data is from a distribution seen during training. In this work, we compare the effect of dataset embeddings in mono-lingual settings, multi-lingual settings, and with predicted data source label in a zero-shot setting. We evaluate on three morphosyntactic tasks: morphological tagging, lemmatization, and dependency parsing, and use 104 datasets, 66 languages, and two different dataset grouping strategies. Performance increases are highest when the datasets are of the same language, and we know from which distribution the test-instance is drawn. In contrast, for setups where the data is from an unseen distribution, performance increase vanishes.

Automatic coreference resolution is understudied in Danish even though most of the Danish Dependency Treebank (Buch-Kromann, 2003) is annotated with coreference relations. This paper describes a conversion of its partial, yet well-documented, coreference relations into coreference clusters and the training and evaluation of coreference models on this data. To the best of our knowledge, these are the first publicly available, neural coreference models for Danish. We also present a new entity linking annotation on the dataset using WikiData identifiers, a named entity disambiguation (NED) dataset, and a larger automatically created NED dataset enabling wikily supervised NED models. The entity linking annotation is benchmarked using a state-of-the-art neural entity disambiguation model.

We propose Cartography Active Learning (CAL), a novel Active Learning (AL) algorithm that exploits the behavior of the model on individual instances during training as a proxy to find the most informative instances for labeling. CAL is inspired by data maps, which were recently proposed to derive insights into dataset quality (Swayamdipta et al., 2020). We compare our method on popular text classification tasks to commonly used AL strategies, which instead rely on post-training behavior. We demonstrate that CAL is competitive to other common AL methods, showing that training dynamics derived from small seed data can be successfully used for AL. We provide insights into our new AL method by analyzing batch-level statistics utilizing the data maps. Our results further show that CAL results in a more data-efficient learning strategy, achieving comparable or better results with considerably less training data.

Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remain largely unexplored in cross-lingual setups. We harness this genre metadata as a weak supervision signal for targeted data selection in zero-shot dependency parsing. Specifically, we project treebank-level genre information to the finer-grained sentence level, with the goal to amplify information implicitly stored in unsupervised contextualized representations. We demonstrate that genre is recoverable from multilingual contextual embeddings and that it provides an effective signal for training data selection in cross-lingual, zero-shot scenarios. For 12 low-resource language treebanks, six of which are test-only, our genre-specific methods significantly outperform competitive baselines as well as recent embedding-based methods for data selection. Moreover, genre-based data selection provides new state-of-the-art results for three of these target languages.

Evaluation is of paramount importance in data-driven research fields such as Natural Language Processing (NLP) and Computer Vision (CV). Current evaluation practice largely hinges on the existence of a single “ground truth” against which we can meaningfully compare the prediction of a model. However, this comparison is flawed for two reasons. 1) In many cases, more than one answer is correct. 2) Even where there is a single answer, disagreement among annotators is ubiquitous, making it difficult to decide on a gold standard. We argue that the current methods of adjudication, agreement, and evaluation need serious reconsideration. Some researchers now propose to minimize disagreement and to fix datasets. We argue that this is a gross oversimplification, and likely to conceal the underlying complexity. Instead, we suggest that we need to better capture the sources of disagreement to improve today’s evaluation practice. We discuss three sources of disagreement: from the annotator, the data, and the context, and show how this affects even seemingly objective tasks. Datasets with multiple annotations are becoming more common, as are methods to integrate disagreement into modeling. The logical next step is to extend this to evaluation.

This paper introduces DAN+, a new multi-domain corpus and annotation guidelines for Dan-ish nested named entities (NEs) and lexical normalization to support research on cross-lingualcross-domain learning for a less-resourced language. We empirically assess three strategies tomodel the two-layer Named Entity Recognition (NER) task. We compare transfer capabilitiesfrom German versus in-language annotation from scratch. We examine language-specific versusmultilingual BERT, and study the effect of lexical normalization on NER. Our results show that 1) the most robust strategy is multi-task learning which is rivaled by multi-label decoding, 2) BERT-based NER models are sensitive to domain shifts, and 3) in-language BERT and lexicalnormalization are the most beneficial on the least canonical data. Our results also show that anout-of-domain setup remains challenging, while performance on news plateaus quickly. Thishighlights the importance of cross-domain evaluation of cross-lingual transfer.

Deep neural networks excel at learning from labeled data and achieve state-of-the-art results on a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift, remains a challenge. Motivated by the latest advances, in this survey we review neural unsupervised domain adaptation techniques which do not require labeled target domain data. This is a more challenging yet a more widely applicable setup. We outline methods, from early traditional non-neural methods to pre-trained model transfer. We also revisit the notion of domain, and we uncover a bias in the type of Natural Language Processing tasks which received most attention. Lastly, we outline future directions, particularly the broader need for out-of-distribution generalization of future NLP.

With the COVID-19 pandemic raging world-wide since the beginning of the 2020 decade, the need for monitoring systems to track relevant information on social media is vitally important. This paper describes our submission to the WNUT-2020 Task 2: Identification of informative COVID-19 English Tweets. We investigate the effectiveness for a variety of classification models, and found that domain-specific pre-trained BERT models lead to the best performance. On top of this, we attempt a variety of ensembling strategies, but these attempts did not lead to further improvements. Our final best model, the standalone CT-BERT model, proved to be highly competitive, leading to a shared first place in the shared task. Our results emphasize the importance of domain and task-related pre-training.

This paper describes a system that aims at assessing humour intensity in edited news headlines as part of the 7th task of SemEval-2020 on “Humor, Emphasis and Sentiment”. Various factors need to be accounted for in order to assess the funniness of an edited headline. We propose an architecture that uses hand-crafted features, knowledge bases and a language model to understand humour, and combines them in a regression model. Our system outperforms two baselines. In general, automatic humour assessment remains a difficult task.

The identification of communication techniques in news articles such as propaganda is important, as such techniques can influence the opinions of large numbers of people. Most work so far focused on the identification at the news article level. Recently, a new dataset and shared task has been proposed for the identification of propaganda techniques at the finer-grained span level. This paper describes our system submission to the subtask of technique classification (TC) for the SemEval 2020 shared task on detection of propaganda techniques in news articles. We propose a method of combining neural BERT representations with hand-crafted features via stacked generalization. Our model has the added advantage that it combines the power of contextual representations from BERT with simple span-based and article-based global features. We present an ablation study which shows that even though BERT representations are very powerful also for this task, BERT still benefits from being combined with carefully designed task-specific features.

Biomedical event extraction is a crucial task in order to automatically extract information from the increasingly growing body of biomedical literature. Despite advances in the methods in recent years, most event extraction systems are still evaluated in-domain and on complete event structures only. This makes it hard to determine the performance of intermediate stages of the task, such as edge detection, across different corpora. Motivated by these limitations, we present the first cross-domain study of edge detection for biomedical event extraction. We analyze differences between five existing gold standard corpora, create a standardized benchmark corpus, and provide a strong baseline model for edge detection. Experiments show a large drop in performance when the baseline is applied on out-of-domain data, confirming the need for domain adaptation methods for the task. To encourage research efforts in this direction, we make both the data and the baseline available to the research community: https://www.cosbi.eu/cfx/9985.

We introduce Biomedical Event Extraction as Sequence Labeling (BeeSL), a joint end-to-end neural information extraction model. BeeSL recasts the task as sequence labeling, taking advantage of a multi-label aware encoding strategy and jointly modeling the intermediate tasks via multi-task learning. BeeSL is fast, accurate, end-to-end, and unlike current methods does not require any external knowledge base or preprocessing tools. BeeSL outperforms the current best system (Li et al., 2019) on the Genia 2011 benchmark by 1.57% absolute F1 score reaching 60.22% F1, establishing a new state of the art for the task. Importantly, we also provide first results on biomedical event extraction without gold entity information. Empirical results show that BeeSL’s speed and accuracy makes it a viable approach for large-scale real-world scenarios.

We study the issue of catastrophic forgetting in the context of neural multimodal approaches to Visual Question Answering (VQA). Motivated by evidence from psycholinguistics, we devise a set of linguistically-informed VQA tasks, which differ by the types of questions involved (Wh-questions and polar questions). We test what impact task difficulty has on continual learning, and whether the order in which a child acquires question types facilitates computational models. Our results show that dramatic forgetting is at play and that task difficulty and order matter. Two well-known current continual learning methods mitigate the problem only to a limiting degree.

We propose a grounded dialogue state encoder which addresses a foundational issue on how to integrate visual grounding with dialogue system components. As a test-bed, we focus on the GuessWhat?! game, a two-player game where the goal is to identify an object in a complex visual scene by asking a sequence of yes/no questions. Our visually-grounded encoder leverages synergies between guessing and asking questions, as it is trained jointly using multi-task learning. We further enrich our model via a cooperative learning regime. We show that the introduction of both the joint architecture and cooperative learning lead to accuracy improvements over the baseline system. We compare our approach to an alternative system which extends the baseline with reinforcement learning. Our in-depth analysis shows that the linguistic skills of the two models differ dramatically, despite approaching comparable performance levels. This points at the importance of analyzing the linguistic output of competing systems beyond numeric comparison solely based on task success.

Readers’ eye movements used as part of the training signal have been shown to improve performance in a wide range of Natural Language Processing (NLP) tasks. Previous work uses gaze data either at the type level or at the token level and mostly from a single eye-tracking corpus. In this paper, we analyze type vs token-level integration options with eye tracking data from two corpora to inform two syntactic sequence labeling problems: binary phrase chunking and part-of-speech tagging. We show that using globally-aggregated measures that capture the central tendency or variability of gaze data is more beneficial than proposed local views which retain individual participant information. While gaze data is informative for supervised POS tagging, which complements previous findings on unsupervised POS induction, almost no improvement is obtained for binary phrase chunking, except for a single specific setup. Hence, caution is warranted when using gaze data as signal for NLP, as no single view is robust over tasks, modeling choice and gaze corpus.

Word embeddings have undoubtedly revolutionized NLP. However, pretrained embeddings do not always work for a specific task (or set of tasks), particularly in limited resource setups. We introduce a simple yet effective, self-supervised post-processing method that constructs task-specialized word representations by picking from a menu of reconstructing transformations to yield improved end-task performance (MORTY). The method is complementary to recent state-of-the-art approaches to inductive transfer via fine-tuning, and forgoes costly model architectures and annotation. We evaluate MORTY on a broad range of setups, including different word embedding methods, corpus sizes and end-task semantics. Finally, we provide a surprisingly simple recipe to obtain specialized embeddings that better fit end-tasks.

More and more evidence is appearing that integrating symbolic lexical knowledge into neural models aids learning. This contrasts the widely-held belief that neural networks largely learn their own feature representations. For example, recent work has shows benefits of integrating lexicons to aid cross-lingual part-of-speech (PoS). However, little is known on how complementary such additional information is, and to what extent improvements depend on the coverage and quality of these external resources. This paper seeks to fill this gap by providing a thorough analysis on the contributions of lexical resources for cross-lingual PoS tagging in neural times.

Danish is a North Germanic language spoken principally in Denmark, a country with a long tradition of technological and scientific innovation. However, the language has received relatively little attention from a technological perspective. In this paper, we review Natural Language Processing (NLP) research, digital resources and tools which have been developed for Danish. We find that availability of models and tools is limited, which calls for work that lifts Danish NLP a step closer to the privileged languages. Dansk abstrakt: Dansk er et nordgermansk sprog, talt primært i kongeriget Danmark, et land med stærk tradition for teknologisk og videnskabelig innovation. Det danske sprog har imidlertid været genstand for relativt begrænset opmærksomhed, teknologisk set. I denne artikel gennemgår vi sprogteknologi-forskning, -ressourcer og -værktøjer udviklet for dansk. Vi konkluderer at der eksisterer et fåtal af modeller og værktøjer, hvilket indbyder til forskning som løfter dansk sprogteknologi i niveau med mere priviligerede sprog.

Named Entity Recognition (NER) has greatly advanced by the introduction of deep neural architectures. However, the success of these methods depends on large amounts of training data. The scarcity of publicly-available human-labeled datasets has resulted in limited evaluation of existing NER systems, as is the case for Danish. This paper studies the effectiveness of cross-lingual transfer for Danish, evaluates its complementarity to limited gold data, and sheds light on performance of Danish NER.

Novel neural models have been proposed in recent years for learning under domain shift. Most models, however, only evaluate on a single task, on proprietary datasets, or compare to weak baselines, which makes comparison of models difficult. In this paper, we re-evaluate classic general-purpose bootstrapping approaches in the context of neural networks under domain shifts vs. recent neural approaches and propose a novel multi-task tri-training method that reduces the time and space complexity of classic tri-training. Extensive experiments on two benchmarks for part-of-speech tagging and sentiment analysis are negative: while our novel method establishes a new state-of-the-art for sentiment analysis, it does not fare consistently the best. More importantly, we arrive at the somewhat surprising conclusion that classic tri-training, with some additions, outperforms the state-of-the-art for NLP. Hence classic approaches constitute an important and strong baseline.

Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform dependent. Cross-lingual embeddings circumvent some of these limitations, but capture gender-specific style less. We propose an alternative: bleaching text, i.e., transforming lexical strings into more abstract features. This study provides evidence that such features allow for better transfer across languages. Moreover, we present a first study on the ability of humans to perform cross-lingual gender prediction. We find that human predictive power proves similar to that of our bleached models, and both perform better than lexical models.

We present our submission to the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM). We focus on evaluating a range of features for the task, including user-derived measures, while examining how far we can get with a simple linear classifier. Our analysis reveals that errors differ per exercise format, which motivates our final and best-performing system: a task-wise (per exercise-format) model.

Written text transmits a good deal of nonverbal information related to the author’s identity and social factors, such as age, gender and personality. However, it is less known to what extent behavioral biometric traces transmit such information. We use typist data to study the predictiveness of authorship, and present first experiments on predicting both age and gender from keystroke dynamics. Our results show that the model based on keystroke features, while being two orders of magnitude smaller, leads to significantly higher accuracies for authorship than the text-based system. For user attribute prediction, the best approach is to combine the two, suggesting that extralinguistic factors are disclosed to a larger degree in written text, while author identity is better transmitted in typing behavior.

Neural part-of-speech (POS) taggers are known to not perform well with little training data. As a step towards overcoming this problem, we present an architecture for learning more robust neural POS taggers by jointly training a hierarchical, recurrent model and a recurrent character-based sequence-to-sequence network supervised using an auxiliary objective. This way, we introduce stronger character-level supervision into the model, which enables better generalization to unseen words and provides regularization, making our encoding less prone to overfitting. We experiment with three auxiliary tasks: lemmatization, character-based word autoencoding, and character-based random string autoencoding. Experiments with minimal amounts of labeled data on 34 languages show that our new architecture outperforms a single-task baseline and, surprisingly, that, on average, raw text autoencoding can be as beneficial for low-resource POS tagging as using lemma information. Our neural POS tagger closes the gap to a state-of-the-art POS tagger (MarMoT) for low-resource scenarios by 43%, even outperforming it on languages with templatic morphology, e.g., Arabic, Hebrew, and Turkish, by some margin.

In this paper we present the results of our participation in the Discriminating between Dutch and Flemish in Subtitles VarDial 2018 shared task. We try techniques proven to work well for discriminating between language varieties as well as explore the potential of using syntactic features, i.e. hierarchical syntactic subtrees. We experiment with different combinations of features. Discriminating between these two languages turned out to be a very hard task, not only for a machine: human performance is only around 0.51 F1 score; our best system is still a simple Naive Bayes model with word unigrams and bigrams. The system achieved an F1 score (macro) of 0.62, which ranked us 4th in the shared task.

a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource languages. The model exploits annotation projection, instance selection, tag dictionaries, morphological lexicons, and distributed representations, all in a uniform framework. The approach is simple, yet surprisingly effective, resulting in a new state of the art without access to any gold annotated data.

We present All-In-1, a simple model for multilingual text classification that does not require any parallel data. It is based on a traditional Support Vector Machine classifier exploiting multilingual word embeddings and character n-grams. Our model is simple, easily extendable yet very effective, overall ranking 1st (out of 12 teams) in the IJCNLP 2017 shared task on customer feedback analysis in four languages: English, French, Japanese and Spanish.

Domain similarity measures can be used to gauge adaptability and select suitable data for transfer learning, but existing approaches define ad hoc measures that are deemed suitable for respective tasks. Inspired by work on curriculum learning, we propose to learn data selection measures using Bayesian Optimization and evaluate them across models, domains and tasks. Our learned measures outperform existing domain similarity measures significantly on three tasks: sentiment analysis, part-of-speech tagging, and parsing. We show the importance of complementing similarity with diversity, and that learned measures are–to some degree–transferable across models, domains, and even tasks.

Multitask learning has been applied successfully to a range of tasks, mostly morphosyntactic. However, little is known on when MTL works and whether there are data characteristics that help to determine the success of MTL. In this paper we evaluate a range of semantic sequence labeling tasks in a MTL setup. We examine different auxiliary task configurations, amongst which a novel setup, and correlate their impact to data-dependent conditions. Our results show that MTL is not always effective, because significant improvements are obtained only for 1 out of 5 tasks. When successful, auxiliary tasks with compact and more uniform label distributions are preferable.

We present UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of specific dependency head rules. UDP features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD. The parser has very few parameters and distinctly robust to domain change across languages.

We address the challenge of cross-lingual POS tagger evaluation in absence of manually annotated test data. We put forth and evaluate two dictionary-based metrics. On the tasks of accuracy prediction and system ranking, we reveal that these metrics are reliable enough to approximate test set-based evaluation, and at the same time lean enough to support assessment for truly low-resource languages.

We present the results of our participation in the VarDial 4 shared task on discriminating closely related languages. Our submission includes simple traditional models using linear support vector machines (SVMs) and a neural network (NN). The main idea was to leverage language group information. We did so with a two-layer approach in the traditional model and a multi-task objective in the neural network case. Our results confirm earlier findings: simple traditional models outperform neural networks consistently for this task, at least given the amount of systems we could examine in the available time. Our two-layer linear SVM ranked 2nd in the shared task.

Does normalization help Part-of-Speech (POS) tagging accuracy on noisy, non-canonical data? To the best of our knowledge, little is known on the actual impact of normalization in a real-world scenario, where gold error detection is not available. We investigate the effect of automatic normalization on POS tagging of tweets. We also compare normalization to strategies that leverage large amounts of unlabeled data kept in its raw form. Our results show that normalization helps, but does not add consistently beyond just word embedding layer initialization. The latter approach yields a tagging model that is competitive with a Twitter state-of-the-art tagger.

We present the RUG-SU team’s submission at the Native Language Identification Shared Task 2017. We combine several approaches into an ensemble, based on spelling error features, a simple neural network using word representations, a deep residual network using word and character features, and a system based on a recurrent neural network. Our best system is an ensemble of neural networks, reaching an F1 score of 0.8323. Although our system is not the highest ranking one, we do outperform the baseline by far.

In this paper, we explore the performance of a linear SVM trained on language independent character features for the NLI Shared Task 2017. Our basic system (GRONINGEN) achieves the best performance (87.56 F1-score) on the evaluation set using only 1-9 character n-grams as features. We compare this against several ensemble and meta-classifiers in order to examine how the linear system fares when combined with other, especially non-linear classifiers. Special emphasis is placed on the topic bias that exists by virtue of the assessment essay prompt distribution.

We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages. Our annotation projection-based approach yields tagging and parsing models for over 100 languages. All that is needed are freely available parallel texts, and taggers and parsers for resource-rich languages. The empirical evaluation across 30 test languages shows that our method consistently provides top-level accuracies, close to established upper bounds, and outperforms several competitive baselines.

Real world data differs radically from the benchmark corpora we use in NLP, resulting in large performance drops. The reason for this problem is obvious: NLP models are trained on limited samples from canonical varieties considered standard. However, there are many dimensions, e.g., sociodemographic, language, genre, sentence type, etc. on which texts can differ from the standard. The solution is not obvious: we cannot control for all factors, and it is not clear how to best go beyond the current practice of training on homogeneous data from a single domain and language. In this talk, I review the notion of canonicity, and how it shapes our community’s approach to language. I argue for the use of fortuitous data. Fortuitous data is data out there that just waits to be harvested. It includes data which is in plain sight, but is often neglected, and more distant sources like behavioral data, which first need to be refined. They provide additional contexts and a myriad of opportunities to build more adaptive language technology, some of which I will explore in this talk.

Personality profiling is the task of detecting personality traits of authors based on writing style. Several personality typologies exist, however, the Briggs-Myer Type Indicator (MBTI) is particularly popular in the non-scientific community, and many people use it to analyse their own personality and talk about the results online. Therefore, large amounts of self-assessed data on MBTI are readily available on social-media platforms such as Twitter. We present a novel corpus of tweets annotated with the MBTI personality type and gender of their author for six Western European languages (Dutch, German, French, Italian, Portuguese and Spanish). We outline the corpus creation and annotation, show statistics of the obtained data distributions and present first baselines on Myers-Briggs personality profiling and gender prediction for all six languages.

Keystroke dynamics have been extensively used in psycholinguistic and writing research to gain insights into cognitive processing. But do keystroke logs contain actual signal that can be used to learn better natural language processing models? We postulate that keystroke dynamics contain information about syntactic structure that can inform shallow syntactic parsing. To test this hypothesis, we explore labels derived from keystroke logs as auxiliary task in a multi-task bidirectional Long Short-Term Memory (bi-LSTM). Our results show promising results on two shallow syntactic parsing tasks, chunking and CCG supertagging. Our model is simple, has the advantage that data can come from distinct sources, and produces models that are significantly better than models trained on the text annotations alone.

We experiment with different ways of training LSTM networks to predict RST discourse trees. The main challenge for RST discourse parsing is the limited amounts of training data. We combat this by regularizing our models using task supervision from related tasks as well as alternative views on discourse structures. We show that a simple LSTM sequential discourse parser takes advantage of this multi-view and multi-task framework with 12-15% error reductions over our baseline (depending on the metric) and results that rival more complex state-of-the-art parsers.

We propose a novel semantic tagging task, semtagging, tailored for the purpose of multilingual semantic parsing, and present the first tagger using deep residual networks (ResNets). Our tagger uses both word and character representations, and includes a novel residual bypass architecture. We evaluate the tagset both intrinsically on the new task of semantic tagging, as well as on Part-of-Speech (POS) tagging. Our system, consisting of a ResNet and an auxiliary loss function predicting our semantic tags, significantly outperforms prior results on English Universal Dependencies POS tagging (95.71% accuracy on UD v1.2 and 95.67% accuracy on UD v1.3).

In this paper we present SenTube – a dataset of user-generated comments on YouTube videos annotated for information content and sentiment polarity. It contains annotations that allow to develop classifiers for several important NLP tasks: (i) sentiment analysis, (ii) text categorization (relatedness of a comment to video and/or product), (iii) spam detection, and (iv) prediction of comment informativeness. The SenTube corpus favors the development of research on indexing and searching YouTube videos exploiting information derived from comments. The corpus will cover several languages: at the moment, we focus on English and Italian, with Spanish and Dutch parts scheduled for the later stages of the project. For all the languages, we collect videos for the same set of products, thus offering possibilities for multi- and cross-lingual experiments. The paper provides annotation guidelines, corpus statistics and annotator agreement details.

Several works in Natural Language Processing have recently looked into part-of-speech annotation of Twitter data and typically used their own data sets. Since conventions on Twitter change rapidly, models often show sample bias. Training on a combination of the existing data sets should help overcome this bias and produce more robust models than any trained on the individual corpora. Unfortunately, combining the existing corpora proves difficult: many of the corpora use proprietary tag sets that have little or no overlap. Even when mapped to a common tag set, the different corpora systematically differ in their treatment of various tags and tokens. This includes both pre-processing decisions, as well as default labels for frequent tokens, thus exhibiting data bias and label bias, respectively. Only if we address these biases can we combine the existing data sets to also overcome sample bias. We present a systematic study of several Twitter POS data sets, the problems of label and data bias, discuss their effects on model performance, and show how to overcome them to learn models that perform well on various test sets, achieving relative error reduction of up to 21%.

We examine the performance of three dependency parsing systems, in particular, their performance variation across Wikipedia domains. We assess the performance variation of (i) Alpino, a deep grammar-based system coupled with a statistical disambiguation versus (ii) MST and Malt, two purely data-driven statistical dependency parsing systems. The question is how the performance of each parser correlates with simple statistical measures of the text (e.g. sentence length, unknown word rate, etc.). This would give us an idea of how sensitive the different systems are to domain shifts, i.e. which system is more in need for domain adaptation techniques. To this end, we extend the statistical measures used by Zhang and Wang (2009) for English and evaluate the systems on several Wikipedia domains by focusing on a freer word-order language, Dutch. The results confirm the general findings of Zhang and Wang (2009), i.e. different parsing systems have different sensitivity against various statistical measure of the text, where the highest correlation to parsing accuracy was found for the measure we added, sentence perplexity.

Modern statistical parsers are trained on large annotated corpora (treebanks). These treebanks usually consist of sentences addressing different subdomains (e.g. sports, politics, music), which implies that the statistics gathered by current statistical parsers are mixtures of subdomains of language use. In this paper we present a method that exploits raw subdomain corpora gathered from the web to introduce subdomain sensitivity into a given parser. We employ statistical techniques for creating an ensemble of domain sensitive parsers, and explore methods for amalgamating their predictions. Our experiments show that introducing domain sensitivity by exploiting raw corpora can improve over a tough, state-of-the-art baseline.

This paper presents an on-going project aiming at enhancing the OPAC (Online Public Access Catalog) search system of the Library of the Free University of Bozen-Bolzano with multilingual access. The Multilingual search system (MUSIL), we have developed, integrates advanced linguistic technologies in a user friendly interface and bridges the gap between the world of free text search and the world of conceptual librarian search. In this paper we present the architecture of the system, its interface and preliminary evaluations of the precision of the search results.