Improvements in language models’ capabilities have pushed their applications towards longer contexts, making long-context evaluation and development an active research area. However, many disparate use-cases are grouped together under the umbrella term of “long-context”, defined simply by the total length of the model’s input, including - for example - Needle-in-a-Haystack tasks, book summarization, and information aggregation. Given their varied difficulty, in this position paper we argue that conflating different tasks by their context length is unproductive. As a community, we require a more precise vocabulary to understand what makes long-context tasks similar or different. We propose to unpack the taxonomy of long-context based on the properties that make them more difficult with longer contexts. We propose two orthogonal axes of difficulty: (I) Diffusion: How hard is it to find the necessary information in the context? (II) Scope: How much necessary information is there to find? We survey the literature on long-context, provide justification for this taxonomy as an informative descriptor, and situate the literature with respect to it. We conclude that the most difficult and interesting settings, whose necessary information is very long and highly diffused within the input, is severely under-explored. By using a descriptive vocabulary and discussing the relevant properties of difficulty in long-context, we can implement more informed research in this area. We call for a careful design of tasks and benchmarks with distinctly long context, taking into account the characteristics that make it qualitatively different from shorter context.

Current Text-to-Code models demonstrate impressive capabilities in generating executable code from natural language snippets. However, current studies focus on technical instructions and programmer-oriented language, and it is an open question whether these models can effectively translate natural language descriptions given by non-technical users and express complex goals, to an executable program that contains an intricate flow—composed of API access and control structures as loops, conditions, and sequences. To unlock the challenge of generating a complete program from a plain non-technical description we present NoviCode, a novel NL Programming task, which takes as input an API and a natural language description by a novice non-programmer, and provides an executable program as output. To assess the efficacy of models on this task, we provide a novel benchmark accompanied by test suites wherein the generated program code is assessed not according to their form, but according to their functional execution. Our experiments show that, first, NoviCode is indeed a challenging task in the code synthesis domain, and that generating complex code from non-technical instructions goes beyond the current Text-to-Code paradigm. Second, we show that a novel approach wherein we align the NL utterances with the compositional hierarchical structure of the code, greatly enhances the performance of LLMs on this task, compared with the end-to-end Text-to-Code counterparts.

Similar to vision-and-language navigation (VLN) tasks that focus on bridging the gap between vision and language for embodied navigation, the new Rendezvous (RVS) task requires reasoning over allocentric spatial relationships using non-sequential navigation instructions and maps. However, performance substantially drops in new environments with no training data.Using opensource descriptions paired with coordinates (e.g., Wikipedia) provides training data but suffers from limited spatially-oriented text resulting in low geolocation resolution. We propose a large-scale augmentation method for generating high-quality synthetic data for new environments using readily available geospatial data. Our method constructs a grounded knowledge-graph, capturing entity relationships. Sampled entities and relations (“shop north of school”) generate navigation instructions via (i) generating numerous templates using context-free grammar (CFG) to embed specific entities and relations; (ii) feeding the entities and relation into a large language model (LLM) for instruction generation. A comprehensive evaluation on RVS, showed that our approach improves the 100-meter accuracy by 45.83% on unseen environments. Furthermore, we demonstrate that models trained with CFG-based augmentation achieve superior performance compared with those trained with LLM-based augmentation, both in unseen and seen environments. These findings suggest that the potential advantages of explicitly structuring spatial information for text-based geospatial reasoning in previously unknown, can unlock data-scarce scenarios.

Despite it being the cornerstone of BPE, the most common tokenization algorithm, the importance of compression in the tokenization process is still unclear. In this paper, we argue for the theoretical importance of compression, that can be viewed as 0-gram language modeling where equal probability is assigned to all tokens. We also demonstrate the empirical importance of compression for downstream success of pre-trained language models. We control the compression ability of several BPE tokenizers by varying the amount of documents available during their training: from 1 million documents to a character-based tokenizer equivalent to no training data at all. We then pre-train English language models based on those tokenizers and fine-tune them over several tasks. We show that there is a correlation between tokenizers’ compression and models’ downstream performance, suggesting that compression is a reliable intrinsic indicator of tokenization quality. These correlations are more pronounced for generation tasks (over classification) or for smaller models (over large ones). We replicated a representative part of our experiments on Turkish and found similar results, confirming that our results hold for languages with typological characteristics dissimilar to English. We conclude that building better compressing tokenizers is a fruitful avenue for further research and for improving overall model performance.

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a multilingual LLM affects instruction-following across languages from the pre-training corpus. We first show that many languages transfer some instruction-following capabilities to other languages from even monolingual tuning. Furthermore, we find that only 40 multilingual examples integrated in an English tuning set substantially improve multilingual instruction-following, both in seen and unseen languages during tuning. In general, we observe that models tuned on multilingual mixtures exhibit comparable or superior performance in multiple languages compared to monolingually tuned models, despite training on 10x fewer examples in those languages. Finally, we find that diversifying the instruction tuning set with even just 2-4 languages significantly improves cross-lingual generalization. Our results suggest that building massively multilingual instruction-tuned models can be done with only a very small set of multilingual instruction-responses.

Syntactic parsing remains a critical tool for relation extraction and information extraction, especially in resource-scarce languages where LLMs are lacking. Yet in morphologically rich languages (MRLs), where parsers need to identify multiple lexical units in each token, existing systems suffer in latency and setup complexity. Some use a pipeline to peel away the layers: first segmentation, then morphology tagging, and then syntax parsing; however, errors in earlier layers are then propagated forward. Others use a joint architecture to evaluate all permutations at once; while this improves accuracy, it is notoriously slow. In contrast, and taking Hebrew as a test case, we present a new “flipped pipeline”: decisions are made directly on the whole-token units by expert classifiers, each one dedicated to one specific task. The classifier predictions are independent of one another, and only at the end do we synthesize their predictions. This blazingly fast approach requires only a single huggingface call, without the need for recourse to lexicons or linguistic resources. When trained on the same training set used in previous studies, our model achieves near-SOTA performance on a wide array of Hebrew NLP tasks. Furthermore, when trained on a newly enlarged training corpus, our model achieves a new SOTA for Hebrew POS tagging and dependency parsing. We release this new SOTA model to the community. Because our architecture does not rely on any language-specific resources, it can serve as a model to develop similar parsers for other MRLs.

Large Vision-Language Models (LVLMs) are an extension of Large Language Models (LLMs) that facilitate processing both image and text inputs, expanding AI capabilities. However, LVLMs struggle with object hallucinations due to their reliance on text cues and learned object co-occurrence biases. While most research quantifies these hallucinations, mitigation strategies are still lacking. Our study introduces a Language Contrastive Decoding (LCD) algorithm that adjusts LVLM outputs based on LLM distribution confidence levels, effectively reducing object hallucinations. We demonstrate the advantages of LCD in leading LVLMs, showing up to %4 improvement in POPE F1 scores and up to %36 reduction in CHAIR scores on the COCO validation set, while also improving captioning quality scores. Our method effectively improves LVLMs without needing complex post-processing or retraining, and is easily applicable to different models. Our findings highlight the potential of further exploration of LVLM-specific decoding algorithms.

While large language models (LLMs) excel in various natural language tasks in English, their performance in low-resource languages like Hebrew, especially for generative tasks such as abstractive summarization, remains unclear. The high morphological richness in Hebrew adds further challenges due to the ambiguity in sentence comprehension and the complexities in meaning construction.In this paper, we address this evaluation and resource gap by introducing HeSum, a novel benchmark dataset specifically designed for Hebrew abstractive text summarization. HeSum consists of 10,000 article-summary pairs sourced from Hebrew news websites written by professionals. Linguistic analysis confirms HeSum’s high abstractness and unique morphological challenges. We show that HeSum presents distinct difficulties even for state-of-the-art LLMs, establishing it as a valuable testbed for advancing generative language technology in Hebrew, and MRLs generative challenges in general.

Large language models hold significant promise in multilingual applications. However, inherent biases stemming from predominantly English-centric pre-training have led to the widespread practice of pre-translation, i.e., translating non-English inputs to English before inference, leading to complexity and information loss. This study re-evaluates the need for pre-translation in the context of PaLM2 models, which have been established as highly performant in multilingual tasks. We offer a comprehensive investigation across 108 languages and 6 diverse benchmarks, including open-end generative tasks, which were excluded from previous similar studies. Our findings challenge the pre-translation paradigm established in prior research, highlighting the advantages of direct inference in PaLM2. Specifically, PaLM2-L consistently outperforms pre-translation in 94 out of 108 languages. These findings pave the way for more efficient and effective multilingual applications, alleviating the limitations associated with pre-translation and unlocking linguistic authenticity.

The concept of acquired spatial knowledge is crucial in spatial cognitive research, particularly when it comes to communicating routes. However, NLP navigation studies often overlook the impact of acquired knowledge on textual descriptions. Current navigation studies concentrate on egocentric local descriptions (e.g., ‘it will be on your right’) that require reasoning over the agent’s local perception. These instructions are typically given in a sequence of steps, with each action-step explicitly mentioned and followed by a landmark that the agent can use to verify that they are on the correct path (e.g., ‘turn right and then you will see...’). In contrast, descriptions based on knowledge acquired through a map provide a complete view of the environment and capture its compositionality. These instructions typically contain allocentric relations, are non-sequential, with implicit actions and multiple spatial relations without any verification (e.g., ‘south of Central Park and a block north of a police station’). This paper introduces the Rendezvous (RVS) task and dataset, which includes 10,404 examples of English geospatial instructions for reaching a target location using map-knowledge. Our analysis reveals that RVS exhibits a richer use of spatial allocentric relations, and requires resolving more spatial relations simultaneously compared to previous text-based navigation benchmarks.

Contemporary multilingual dependency parsers can parse a diverse set of languages, but for Morphologically Rich Languages (MRLs), performance is attested to be lower than other languages. The key challenge is that, due to high morphological complexity and ambiguity of the space-delimited input tokens, the linguistic units that act as nodes in the tree are not known in advance. Pre-neural dependency parsers for MRLs subscribed to the joint morpho-syntactic hypothesis, stating that morphological segmentation and syntactic parsing should be solved jointly, rather than as a pipeline where segmentation precedes parsing. However, neural state-of-the-art parsers to date use a strict pipeline. In this paper we introduce a joint neural architecture where a lattice-based representation preserving all morphological ambiguity of the input is provided to an arc-factored model, which then solves the morphological segmentation and syntactic parsing tasks at once. Our experiments on Hebrew, a rich and highly ambiguous MRL, demonstrate state-of-the-art performance on parsing, tagging and segmentation of the Hebrew section of UD, using a single model. This proposed architecture is LLM-based and language agnostic, providing a solid foundation for MRLs to obtain further performance improvements and bridge the gap with other languages.

While large language models (LLMs) excel in various natural language tasks in English, their performance in low-resource languages like Hebrew, especially for generative tasks such as abstractive summarization, remains unclear. The high morphological richness in Hebrew adds further challenges due to the ambiguity in sentence comprehension and the complexities in meaning construction. In this paper, we address this evaluation and resource gap by introducing HeSum, a novel benchmark dataset specifically designed for Hebrew abstractive text summarization. HeSum consists of 10,000 article-summary pairs sourced from Hebrew news websites written by professionals. Linguistic analysis confirms HeSum’s high abstractness and unique morphological challenges. We show that HeSum presents distinct difficulties even for state-of-the-art LLMs, establishing it as a valuable testbed for advancing generative language technology in Hebrew, and MRLs generative challenges in general.

Verbal omissions are complex syntactic phenomena in VP coordination structures. They occur when verbs and (some of) their arguments are omitted from subsequent clauses after being explicitly stated in an initial clause. Recovering these omitted elements is necessary for accurate interpretation of the sentence, and while humans easily and intuitively fill in the missing information, state-of-the-art models continue to struggle with this task. Previous work is limited to small-scale datasets, synthetic data creation methods, and to resolution methods in the dependency-graph level. In this work we propose a conjunct resolution task that operates directly on the text and makes use of a split-and-rephrase paradigm in order to recover the missing elements in the coordination structure. To this end, we first formulate a pragmatic framework of verbal omissions which describes the different types of omissions, and develop an automatic scalable collection method. Based on this method, we curate a large dataset, containing over 10K examples of naturally-occurring verbal omissions with crowd-sourced annotations of the resolved conjuncts. We train various neural baselines for this task, and show that while our best method obtains decent performance, it leaves ample space for improvement. We propose our dataset, metrics and models as a starting point for future research on this topic.

Human communication often involves information gaps between the interlocutors. For example, in an educational dialogue a student often provides an answer that is incomplete, and there is a gap between this answer and the perfect one expected by the teacher. Successful dialogue then hinges on the teacher asking about this gap in an effective manner, thus creating a rich and interactive educational experience. We focus on the problem of generating such gap-focused questions (GFQs) automatically. We define the task, highlight key desired aspects of a good GFQ, and propose a model that satisfies these. Finally, we provide an evaluation by human annotators of our generated questions compared against human generated ones, demonstrating competitive performance.

Recent years have brought great advances into solving morphological tasks, mostly due to powerful neural models applied to various tasks as (re)inflection and analysis. Yet, such morphological tasks cannot be considered solved, especially when little training data is available or when generalizing to previously unseen lemmas. This work explores effects on performance obtained through various ways in which morphological models get access to sub-character phonological features that are often the targets of morphological processes. We design two methods to achieve this goal: one that leaves models as is but manipulates the data to include features instead of characters, and another that manipulates models to take phonological features into account when building representations for phonemes. We elicit phonemic data from standard graphemic data using language-specific grammars for languages with shallow grapheme-to-phoneme mapping, and we experiment with two reinflection models over eight languages. Our results show that our methods yield comparable results to the grapheme-based baseline overall, with minor improvements in some of the languages. All in all, we conclude that patterns in character distributions are likely to allow models to infer the underlying phonological characteristics, even when phonemes are not explicitly represented.

The task of textual geolocation — retrieving the coordinates of a place based on a free-form language description — calls for not only grounding but also natural language understanding and geospatial reasoning. Even though there are quite a few datasets in English used for geolocation, they are currently based on open-source data (Wikipedia and Twitter), where the location of the described place is mostly implicit, such that the location retrieval resolution is limited. Furthermore, there are no datasets available for addressing the problem of textual geolocation in morphologically rich and resource-poor languages, such as Hebrew. In this paper, we present the Hebrew Geo-Location (HeGeL) corpus, designed to collect literal place descriptions and analyze lingual geospatial reasoning. We crowdsourced 5,649 literal Hebrew place descriptions of various place types in three cities in Israel. Qualitative and empirical analysis show that the data exhibits abundant use of geospatial reasoning and requires a novel environmental representation.

Recent work attributes progress in NLP to large language models (LMs) with increased model size and large quantities of pretraining data. Despite this, current state-of-the-art LMs for Hebrew are both under-parameterized and under-trained compared to LMs in other languages. Additionally, previous work on pretrained Hebrew LMs focused on encoder-only models. While the encoder-only architecture is beneficial for classification tasks, it does not cater well for sub-word prediction tasks, such as Named Entity Recognition, when considering the morphologically rich nature of Hebrew. In this paper we argue that sequence-to-sequence generative architectures are more suitable for large LMs in morphologically rich languages (MRLs) such as Hebrew. We demonstrate this by casting tasks in the Hebrew NLP pipeline as text-to-text tasks, for which we can leverage powerful multilingual, pretrained sequence-to-sequence models as mT5, eliminating the need for a separate, specialized, morpheme-based, decoder. Using this approach, our experiments show substantial improvements over previously published results on all existing Hebrew NLP benchmarks. These results suggest that multilingual sequence-to-sequence models present a promising building block for NLP for MRLs.

In the age of information overload, it is more important than ever to discern fact from fiction. From the internet to traditional media, we are constantly confronted with a deluge of information, much of which comes from politicians and other public figures who wield significant influence. In this paper, we introduce HeTrue: a new, publicly available dataset for evaluating the credibility of statements made by Israeli public figures and politicians. This dataset consists of 1021 statements, manually annotated by Israeli professional journalists, for their credibility status. Using this corpus, we set out to assess whether the credibility of statements can be predicted based on the text alone. To establish a baseline, we compare text-only methods with others using additional data like metadata, context, and evidence. Furthermore, we develop several credibility assessment models, including a feature-based model that utilizes linguistic features, and state-of-the-art transformer-based models with contextualized embeddings from a pre-trained encoder. Empirical results demonstrate improved performance when models integrate statement and context, outperforming those relying on the statement text alone. Our best model, which also integrates evidence, achieves a 48.3 F1 Score, suggesting that HeTrue is a challenging benchmark, calling for further work on this task.

The ability to identify and control different kinds of linguistic information encoded in vector representations of words has many use cases, especially for explainability and bias removal. This is usually done via a set of simple classification tasks, termed probes, to evaluate the information encoded in the embedding space. However, the involvement of a trainable classifier leads to entanglement between the probe’s results and the classifier’s nature. As a result, contemporary works on probing include tasks that do not involve training of auxiliary models. In this work we introduce the term indicator tasks for non-trainable tasks which are used to query embedding spaces for the existence of certain properties, and claim that this kind of tasks may point to a direction opposite to probes, and that this contradiction complicates the decision on whether a property exists in an embedding space. We demonstrate our claims with two test cases, one dealing with gender debiasing and another with the erasure of morphological information from embedding spaces. We show that the application of a suitable indicator provides a more accurate picture of the information captured and removed compared to probes. We thus conclude that indicator tasks should be implemented and taken into consideration when eliciting information from embedded representations.

Current benchmarks for Hebrew Natural Language Processing (NLP) focus mainly on morpho-syntactic tasks, neglecting the semantic dimension of language understanding. To bridge this gap, we set out to deliver a Hebrew Machine Reading Comprehension (MRC) dataset, where MRC is to be realized as extractive Question Answering. The morphologically-rich nature of Hebrew poses a challenge to this endeavor: the indeterminacy and non-transparency of span boundaries in morphologically complex forms lead to annotation inconsistencies, disagreements, and flaws of standard evaluation metrics. To remedy this, we devise a novel set of guidelines, a controlled crowdsourcing protocol, and revised evaluation metrics, that are suitable for the morphologically rich nature of the language. Our resulting benchmark, HeQ (Hebrew QA), features 30,147 diverse question-answer pairs derived from both Hebrew Wikipedia articles and Israeli tech news. Our empirical investigation reveals that standard evaluation metrics such as F1 Scores and Exact Match (EM) are not appropriate for Hebrew (and other MRLs), and we propose a relevant enhancement. In addition, our experiments show low correlation between models’ performance on morpho-syntactic tasks and on MRC, which suggests that models that are designed for the former might underperform on semantic-heavy tasks. The development and exploration of HeQ illustrate some of the challenges MRLs pose in natural language understanding (NLU), fostering progression towards more and better NLU models for Hebrew and other MRLs.

Coherence is a linguistic term that refers to the relations between small textual units (sentences, propositions), which make the text logically consistent and meaningful to the reader. With the advances of generative foundational models in NLP, there is a pressing need to automatically assess the human-perceived coherence of automatically generated texts. Up until now, little work has been done on explicitly assessing the coherence of generated texts and analyzing the factors contributing to (in)coherence. Previous work on the topic used other tasks, e.g., sentence reordering, as proxies of coherence, rather than approaching coherence detection heads on. In this paper, we introduce CoheSentia, a novel benchmark of human-perceived coherence of automatically generated texts. Our annotation protocol reflects two perspectives; one is global, assigning a single coherence score, and the other is incremental, scoring sentence by sentence. The incremental method produces an (in)coherence score for each text fragment and also pinpoints reasons for incoherence at that point. Our benchmark contains 500 automatically-generated and human-annotated paragraphs, each annotated in both methods, by multiple raters. Our analysis shows that the inter-annotator agreement in the incremental mode is higher than in the holistic alternative, and our experiments show that standard LMs fine-tuned for coherence detection show varied performance on the different factors contributing to (in)coherence. All in all, these models yield unsatisfactory performance, emphasizing the need for developing more reliable methods for coherence assessment.

Semitic morphologically-rich languages (MRLs) are characterized by extreme word ambiguity. Because most vowels are omitted in standard texts, many of the words are homographs with multiple possible analyses, each with a different pronunciation and different morphosyntactic properties. This ambiguity goes beyond word-sense disambiguation (WSD), and may include token segmentation into multiple word units. Previous research on MRLs claimed that standardly trained pre-trained language models (PLMs) based on word-pieces may not sufficiently capture the internal structure of such tokens in order to distinguish between these analyses.Taking Hebrew as a case study, we investigate the extent to which Hebrew homographs can be disambiguated and analyzed using PLMs. We evaluate all existing models for contextualized Hebrew embeddings on a novel Hebrew homograph challenge sets that we deliver. Our empirical results demonstrate that contemporary Hebrew contextualized embeddings outperform non-contextualized embeddings; and that they are most effective for disambiguating segmentation and morphosyntactic features, less so regarding pure word-sense disambiguation. We show that these embeddings are more effective when the number of word-piece splits is limited, and they are more effective for 2-way and 3-way ambiguities than for 4-way ambiguity. We show that the embeddings are equally effective for homographs of both balanced and skewed distributions, whether calculated as masked or unmasked tokens. Finally, we show that these embeddings are as effective for homograph disambiguation with extensive supervised training as with a few-shot setup.

The 2023 SIGMORPHON–UniMorph shared task on typologically diverse morphological inflection included a wide range of languages: 26 languages from 9 primary language families. The data this year was all lemma-split, to allow testing models’ generalization ability, and structured along the new hierarchical schema presented in (Batsuren et al., 2022). The systems submitted this year, 9 in number, showed ingenuity and innovativeness, including hard attention for explainability and bidirectional decoding. Special treatment was also given by many participants to the newly-introduced data in Japanese, due to the high abundance of unseen Kanji characters in its test set.

Disagreement in natural language annotation has mostly been studied from a perspective of biases introduced by the annotators and the annotation frameworks. Here, we propose to analyze another source of bias—task design bias, which has a particularly strong impact on crowdsourced linguistic annotations where natural language is used to elicit the interpretation of lay annotators. For this purpose we look at implicit discourse relation annotation, a task that has repeatedly been shown to be difficult due to the relations’ ambiguity. We compare the annotations of 1,200 discourse relations obtained using two distinct annotation tasks and quantify the biases of both methods across four different domains. Both methods are natural language annotation tasks designed for crowdsourcing. We show that the task design can push annotators towards certain relations and that some discourse relation senses can be better elicited with one or the other annotation approach. We also conclude that this type of bias should be taken into account when training and testing models.

Large Pre-trained Language Models (PLMs) have become ubiquitous in the development of language understanding technology and lie at the heart of many artificial intelligence advances. While advances reported for English using PLMs are unprecedented, reported advances using PLMs for Hebrew are few and far between. The problem is twofold. First, so far, Hebrew resources for training large language models are not of the same magnitude as their English counterparts. Second, most benchmarks available to evaluate progress in Hebrew NLP require morphological boundaries which are not available in the output of standard PLMs. In this work we remedy both aspects. We present AlephBERT, a large PLM for Modern Hebrew, trained on larger vocabulary and a larger dataset than any Hebrew PLM before. Moreover, we introduce a novel neural architecture that recovers the morphological segments encoded in contextualized embedding vectors. Based on this new morphological component we offer an evaluation suite consisting of multiple tasks and benchmarks that cover sentence-level, word-level and sub-word level analyses. On all tasks, AlephBERT obtains state-of-the-art results beyond contemporary Hebrew baselines. We make our AlephBERT model, the morphological extraction model, and the Hebrew evaluation suite publicly available, for evaluating future Hebrew PLMs.

In recent years, a flurry of morphological datasets had emerged, most notably UniMorph, aa multi-lingual repository of inflection tables. However, the flat structure of the current morphological annotation makes the treatment of some languages quirky, if not impossible, specifically in cases of polypersonal agreement. In this paper we propose a general solution for such cases and expand the UniMorph annotation schema to naturally address this phenomenon, in which verbs agree with multiple arguments using true affixes. We apply this extended schema to one such language, Georgian, and provide a human-verified, accurate and balanced morphological dataset for Georgian verbs. The dataset has 4 times more tables and 6 times more verb forms compared to the existing UniMorph dataset, covering all possible variants of argument marking, demonstrating the adequacy of our proposed scheme. Experiments on a reinflection task show that generalization is easy when the data is split at the form level, but extremely hard when splitting along lemma lines. Expanding the other languages in UniMorph according to this schema is expected to improve both the coverage, consistency and interpretability of this benchmark.

In the domain of Morphology, Inflection is a fundamental and important task that gained a lot of traction in recent years, mostly via SIGMORPHON’s shared-tasks. With average accuracy above 0.9 over the scores of all languages, the task is considered mostly solved using relatively generic neural seq2seq models, even with little data provided. In this work, we propose to re-evaluate morphological inflection models by employing harder train-test splits that will challenge the generalization capacity of the models. In particular, as opposed to the naïve split-by-form, we propose a split-by-lemma method to challenge the performance on existing benchmarks. Our experiments with the three top-ranked systems on the SIGMORPHON’s 2020 shared-task show that the lemma-split presents an average drop of 30 percentage points in macro-average for the 90 languages included. The effect is most significant for low-resourced languages with a drop as high as 95 points, but even high-resourced languages lose about 10 points on average. Our results clearly show that generalizing inflection to unseen lemmas is far from being solved, presenting a simple yet effective means to promote more sophisticated models.

Can we teach models designed for language understanding tasks to track and improve their beliefs through intermediate points in text? Besides making their inner workings more transparent, this would also help make models more reliable and consistent. To this end, we propose a representation learning framework called breakpoint modeling that allows for efficient and robust learning of this type. Given any text encoder and data marked with intermediate states (breakpoints) along with corresponding textual queries viewed as true/false propositions (i.e., the candidate intermediate beliefs of a model), our approach trains models in an efficient and end-to-end fashion to build intermediate representations that facilitate direct querying and training of beliefs at arbitrary points in text, alongside solving other end-tasks. We evaluate breakpoint modeling on a diverse set of NLU tasks including relation reasoning on Cluttr and narrative understanding on bAbI. Using novel proposition prediction tasks alongside these end-tasks, we show the benefit of our T5-based breakpoint transformer over strong conventional representation learning approaches in terms of processing efficiency, belief accuracy, and belief consistency, all with minimal to no degradation on the end-task. To show the feasibility of incorporating our belief tracker into more complex reasoning pipelines, we also obtain state-of-the-art performance on the three-tiered reasoning challenge for the recent TRIP benchmark (23-32% absolute improvement on Tasks 2-3).

While neural language models often perform surprisingly well on natural language understanding (NLU) tasks, their strengths and limitations remain poorly understood. Controlled synthetic tasks are thus an increasingly important resource for diagnosing model behavior. In this work we focus on story understanding, a core competency for NLU systems. However, the main synthetic resource for story understanding, the bAbI benchmark, lacks such a systematic mechanism for controllable task generation. We develop Dyna-bAbI, a dynamic framework providing fine-grained control over task generation in bAbI. We demonstrate our ideas by constructing three new tasks requiring compositional generalization, an important evaluation setting absent from the original benchmark. We tested both special-purpose models developed for bAbI as well as state-of-the-art pre-trained methods, and found that while both approaches solve the original tasks (99% accuracy), neither approach succeeded in the compositional generalization setting, indicating the limitations of the original training data. We explored ways to augment the original data, and found that though diversifying training data was far more useful than simply increasing dataset size, it was still insufficient for driving robust compositional generalization (with 70% accuracy for complex compositions). Our results underscore the importance of highly controllable task generators for creating robust NLU systems through a virtuous cycle of model and data development.

The 2022 Multilingual Representation Learning (MRL) Shared Task was dedicated to clause-level morphology. As the first ever benchmark that defines and evaluates morphology outside its traditional lexical boundaries, the shared task on multilingual clause-level morphology sets the scene for competition across different approaches to morphological modeling, with 3 clause-level sub-tasks: morphological inflection, reinflection and analysis, where systems are required to generate, manipulate or analyze simple sentences centered around a single content lexeme and a set of morphological features characterizing its syntactic clause. This year’s tasks covered eight typologically distinct languages: English, French, German, Hebrew, Russian, Spanish, Swahili and Turkish. The tasks has received submissions of four systems from three teams which were compared to two baselines implementing prominent multilingual learning methods. The results show that modern NLP models are effective in solving morphological tasks even at the clause level. However, there is still room for improvement, especially in the task of morphological analysis.

The Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological inflection tables for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation, and a type-level resource of annotated data in diverse languages realizing that schema. This paper presents the expansions and improvements on several fronts that were made in the last couple of years (since McCarthy et al. (2020)). Collaborative efforts by numerous linguists have added 66 new languages, including 24 endangered languages. We have implemented several improvements to the extraction pipeline to tackle some issues, e.g., missing gender and macrons information. We have amended the schema to use a hierarchical structure that is needed for morphological phenomena like multiple-argument agreement and case stacking, while adding some missing morphological features to make the schema more inclusive. In light of the last UniMorph release, we also augmented the database with morpheme segmentation for 16 languages. Lastly, this new release makes a push towards inclusion of derivational morphology in UniMorph by enriching the data and annotation schema with instances representing derivational processes from MorphyNet.

Obtaining linguistic annotation from novice crowdworkers is far from trivial. A case in point is the annotation of discourse relations, which is a complicated task. Recent methods have obtained promising results by extracting relation labels from either discourse connectives (DCs) or question-answer (QA) pairs that participants provide. The current contribution studies the effect of worker selection and training on the agreement on implicit relation labels between workers and gold labels, for both the DC and the QA method. In Study 1, workers were not specifically selected or trained, and the results show that there is much room for improvement. Study 2 shows that a combination of selection and training does lead to improved results, but the method is cost- and time-intensive. Study 3 shows that a selection-only approach is a viable alternative; it results in annotations of comparable quality compared to annotations from trained participants. The results generalized over both the DC and QA method and therefore indicate that a selection-only approach could also be effective for other crowdsourced discourse annotation tasks.

Understanding the relations between entities denoted by NPs in a text is a critical part of human-like natural language understanding. However, only a fraction of such relations is covered by standard NLP tasks and benchmarks nowadays. In this work, we propose a novel task termed text-based NP enrichment (TNE), in which we aim to enrich each NP in a text with all the preposition-mediated relations—either explicit or implicit—that hold between it and other NPs in the text. The relations are represented as triplets, each denoted by two NPs related via a preposition. Humans recover such relations seamlessly, while current state-of-the-art models struggle with them due to the implicit nature of the problem. We build the first large-scale dataset for the problem, provide the formal framing and scope of annotation, analyze the data, and report the results of fine-tuned language models on the task, demonstrating the challenge it poses to current technology. A webpage with a data-exploration UI, a demo, and links to the code, models, and leaderboard, to foster further research into this challenging problem can be found at: yanaiela.github.io/TNE/.

Abstraction is a core tenet of human cognition and communication. When composing natural language instructions, humans naturally evoke abstraction to convey complex procedures in an efficient and concise way. Yet, interpreting and grounding abstraction expressed in NL has not yet been systematically studied in NLP, with no accepted benchmarks specifically eliciting abstraction in NL. In this work, we set the foundation for a systematic study of processing and grounding abstraction in NLP. First, we deliver a novel abstraction elicitation method and present Hexagons, a 2D instruction-following game. Using Hexagons we collected over 4k naturally occurring visually-grounded instructions rich with diverse types of abstractions. From these data, we derive an instruction-to-execution task and assess different types of neural models. Our results show that contemporary models and modeling practices are substantially inferior to human performance, and that model performance is inversely correlated with the level of abstraction, showing less satisfying performance on higher levels of abstraction. These findings are consistent across models and setups, confirming that abstraction is a challenging phenomenon deserving further attention and study in NLP/AI research.

Morphological tasks use large multi-lingual datasets that organize words into inflection tables, which then serve as training and evaluation data for various tasks. However, a closer inspection of these data reveals profound cross-linguistic inconsistencies, which arise from the lack of a clear linguistic and operational definition of what is a word, and which severely impair the universality of the derived tasks. To overcome this deficiency, we propose to view morphology as a clause-level phenomenon, rather than word-level. It is anchored in a fixed yet inclusive set of features, that encapsulates all functions realized in a saturated clause. We deliver MightyMorph, a novel dataset for clause-level morphology covering 4 typologically different languages: English, German, Turkish, and Hebrew. We use this dataset to derive 3 clause-level morphological tasks: inflection, reinflection and analysis. Our experiments show that the clause-level tasks are substantially harder than the respective word-level tasks, while having comparable complexity across languages. Furthermore, redefining morphology to the clause-level provides a neat interface with contextualized language models (LMs) and allows assessing the morphological knowledge encoded in these models and their usability for morphological tasks. Taken together, this work opens up new horizons in the study of computational morphology, leaving ample space for studying neural morphology cross-linguistically.

Morphological tasks have gained decent popularity within the NLP community in the recent years, with large multi-lingual datasets providing morphological analysis of words, either in or out of context. However, the lack of a clear linguistic definition for words destines the annotative work to be incomplete and mired in inconsistencies, especially cross-linguistically. In this work we expand morphological inflection of words to inflection of sentences to provide true universality disconnected from orthographic traditions of white-space usage. To allow annotation for sentence-inflection we define a morphological annotation scheme by a fixed set of inflectional features. We present a small cross-linguistic dataset including semi-manually generated simple sentences in 4 typologically diverse languages annotated according to our suggested scheme, and show that the task of reinflection gets substantially more difficult but that the change of scope from words to well-defined sentences allows interface with contextualized language models.

Modality is the linguistic ability to describe vents with added information such as how desirable, plausible, or feasible they are. Modality is important for many NLP downstream tasks such as the detection of hedging, uncertainty, speculation, and more. Previous studies that address modality detection in NLP often restrict modal expressions to a closed syntactic class, and the modal sense labels are vastly different across different studies, lacking an accepted standard. Furthermore, these senses are often analyzed independently of the events that they modify. This work builds on the theoretical foundations of the Georgetown Gradable Modal Expressions (GME) work by Rubinstein et al. (2013) to propose an event-based modality detection task where modal expressions can be words of any syntactic class and sense labels are drawn from a comprehensive taxonomy which harmonizes the modal concepts contributed by the different studies. We present experiments on the GME corpus aiming to detect and classify fine-grained modal concepts and associate them with their modified events. We show that detecting and classifying modal expressions is not only feasible, it also improves the detection of modal events in their own right.

Named Entity Recognition (NER) is a fundamental NLP task, commonly formulated as classification over a sequence of tokens. Morphologically rich languages (MRLs) pose a challenge to this basic formulation, as the boundaries of named entities do not necessarily coincide with token boundaries, rather, they respect morphological boundaries. To address NER in MRLs we then need to answer two fundamental questions, namely, what are the basic units to be labeled, and how can these units be detected and classified in realistic settings (i.e., where no gold morphology is available). We empirically investigate these questions on a novel NER benchmark, with parallel token- level and morpheme-level NER annotations, which we develop for Modern Hebrew, a morphologically rich-and-ambiguous language. Our results show that explicitly modeling morphological boundaries leads to improved NER performance, and that a novel hybrid architecture, in which NER precedes and prunes morphological decomposition, greatly outperforms the standard pipeline, where morphological decomposition strictly precedes NER, setting a new performance bar for both Hebrew NER and Hebrew morphological decomposition tasks.

Asking questions about a situation is an inherent step towards understanding it. To this end, we introduce the task of role question generation, which, given a predicate mention and a passage, requires producing a set of questions asking about all possible semantic roles of the predicate. We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage. Unlike most existing approaches to question generation, our approach does not require conditioning on existing answers in the text. Instead, we condition on the type of information to inquire about, regardless of whether the answer appears explicitly in the text, could be inferred from it, or should be sought elsewhere. Our evaluation demonstrates that we generate diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles.

Neural models for the various flavours of morphological reinflection tasks have proven to be extremely accurate given ample labeled data, yet labeled data may be slow and costly to obtain. In this work we aim to overcome this annotation bottleneck by bootstrapping labeled data from a seed as small as five labeled inflection tables, accompanied by a large bulk of unlabeled text. Our bootstrapping method exploits the orthographic and semantic regularities in morphological systems in a two-phased setup, where word tagging based on analogies is followed by word pairing based on distances. Our experiments with the Paradigm Cell Filling Problem over eight typologically different languages show that in languages with relatively simple morphology, orthographic regularities on their own allow inflection models to achieve respectable accuracy. Combined orthographic and semantic regularities alleviate difficulties with particularly complex morpho-phonological systems. We further show that our bootstrapping methods substantially outperform hallucination-based methods commonly used for overcoming the annotation bottleneck in morphological reinflection tasks.

This work investigates the most basic units that underlie contextualized word embeddings, such as BERT — the so-called word pieces. In Morphologically-Rich Languages (MRLs) which exhibit morphological fusion and non-concatenative morphology, the different units of meaning within a word may be fused, intertwined, and cannot be separated linearly. Therefore, when using word-pieces in MRLs, we must consider that: (1) a linear segmentation into sub-word units might not capture the full morphological complexity of words; and (2) representations that leave morphological knowledge on sub-word units inaccessible might negatively affect performance. Here we empirically examine the capacity of word-pieces to capture morphology by investigating the task of multi-tagging in Modern Hebrew, as a proxy to evaluate the underlying segmentation. Our results show that, while models trained to predict multi-tags for complete words outperform models tuned to predict the distinct tags of WPs, we can improve the WPs tag prediction by purposefully constraining the word-pieces to reflect their internal functions. We suggest that linguistically-informed word-pieces schemes, that make the morphological structure explicit, might boost performance for MRLs.

It has been exactly a decade since the first establishment of SPMRL, a research initiative unifying multiple research efforts to address the peculiar challenges of Statistical Parsing for Morphologically-Rich Languages (MRLs). Here we reflect on parsing MRLs in that decade, highlight the solutions and lessons learned for the architectural, modeling and lexical challenges in the pre-neural era, and argue that similar challenges re-emerge in neural architectures for MRLs. We then aim to offer a climax, suggesting that incorporating symbolic ideas proposed in SPMRL terms into nowadays neural architectures has the potential to push NLP for MRLs to a new level. We sketch a strategies for designing Neural Models for MRLs (NMRL), and showcase preliminary support for these strategies via investigating the task of multi-tagging in Hebrew, a morphologically-rich, high-fusion, language.

Syntactic dependencies can be predicted with high accuracy, and are useful for both machine-learned and pattern-based information extraction tasks. However, their utility can be improved. These syntactic dependencies are designed to accurately reflect syntactic relations, and they do not make semantic relations explicit. Therefore, these representations lack many explicit connections between content words, that would be useful for downstream applications. Proposals like English Enhanced UD improve the situation by extending universal dependency trees with additional explicit arcs. However, they are not available to Python users, and are also limited in coverage. We introduce a broad-coverage, data-driven and linguistically sound set of transformations, that makes event-structure and many lexical relations explicit. We present pyBART, an easy-to-use open-source Python library for converting English UD trees either to Enhanced UD graphs or to our representation. The library can work as a standalone package or be integrated within a spaCy NLP pipeline. When evaluated in a pattern-based relation extraction scenario, our representation results in higher extraction scores than Enhanced UD, while requiring fewer patterns.

Crowdsourcing has eased and scaled up the collection of linguistic annotation in recent years. In this work, we follow known methodologies of collecting labeled data for the complement coercion phenomenon. These are constructions with an implied action — e.g., “I started a new book I bought last week”, where the implied action is reading. We aim to collect annotated data for this phenomenon by reducing it to either of two known tasks: Explicit Completion and Natural Language Inference. However, in both cases, crowdsourcing resulted in low agreement scores, even though we followed the same methodologies as in previous work. Why does the same process fail to yield high agreement scores? We specify our modeling schemes, highlight the differences with previous work and provide some insights about the task and possible explanations for the failure. We conclude that specific phenomena require tailored solutions, not only in specialized algorithms, but also in data collection methods.

We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds’ images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions. This setup has been studied in the vision community under the name zero-shot learning from text, focusing on learning to transfer knowledge about visual aspects of birds from seen classes to previously-unseen ones. Here, we suggest focusing on the textual description and distilling from the description the most relevant information to effectively match visual features to the parts of the text that discuss them. Specifically, (1) we propose to leverage the similarity between species, reflected in the similarity between text descriptions of the species. (2) we derive visual summaries of the texts, i.e., extractive summaries that focus on the visual features that tend to be reflected in images. We propose a simple attention-based model augmented with the similarity and visual summaries components. Our empirical results consistently and significantly outperform the state-of-the-art on the largest benchmarks for text-based zero-shot learning, illustrating the critical importance of texts for zero-shot image-recognition.

Standard test sets for supervised learning evaluate in-distribution generalization. Unfortunately, when a dataset has systematic gaps (e.g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture the abilities a dataset is intended to test. We propose a more rigorous annotation paradigm for NLP that helps to close systematic gaps in the test data. In particular, after a dataset is constructed, we recommend that the dataset authors manually perturb the test instances in small but meaningful ways that (typically) change the gold label, creating contrast sets. Contrast sets provide a local view of a model’s decision boundary, which can be used to more accurately evaluate a model’s true linguistic capabilities. We demonstrate the efficacy of contrast sets by creating them for 10 diverse NLP datasets (e.g., DROP reading comprehension, UD parsing, and IMDb sentiment analysis). Although our contrast sets are not explicitly adversarial, model performance is significantly lower on them than on the original test sets—up to 25% in some cases. We release our contrast sets as new evaluation benchmarks and encourage future dataset construction efforts to follow similar annotation processes.

One of the primary tasks of morphological parsers is the disambiguation of homographs. Particularly difficult are cases of unbalanced ambiguity, where one of the possible analyses is far more frequent than the others. In such cases, there may not exist sufficient examples of the minority analyses in order to properly evaluate performance, nor to train effective classifiers. In this paper we address the issue of unbalanced morphological ambiguities in Hebrew. We offer a challenge set for Hebrew homographs — the first of its kind — containing substantial attestation of each analysis of 21 Hebrew homographs. We show that the current SOTA of Hebrew disambiguation performs poorly on cases of unbalanced ambiguity. Leveraging our new dataset, we achieve a new state-of-the-art for all 21 words, improving the overall average F1 score from 0.67 to 0.95. Our resulting annotated datasets are made publicly available for further research.

Morphologically Rich Languages (MRLs) such as Arabic, Hebrew and Turkish often require Morphological Disambiguation (MD), i.e., the prediction of morphological decomposition of tokens into morphemes, early in the pipeline. Neural MD may be addressed as a simple pipeline, where segmentation is followed by sequence tagging, or as an end-to-end model, predicting morphemes from raw tokens. Both approaches are sub-optimal; the former is heavily prone to error propagation, and the latter does not enjoy explicit access to the basic processing units called morphemes. This paper offers MD architecture that combines the symbolic knowledge of morphemes with the learning capacity of neural end-to-end modeling. We propose a new, general and easy-to-implement Pointer Network model where the input is a morphological lattice and the output is a sequence of indices pointing at a single disambiguated path of morphemes. We demonstrate the efficacy of the model on segmentation and tagging, for Hebrew and Turkish texts, based on their respective Universal Dependencies (UD) treebanks. Our experiments show that with complete lattices, our model outperforms all shared-task results on segmenting and tagging these languages. On the SPMRL treebank, our model outperforms all previously reported results for Hebrew MD in realistic scenarios.

Discourse relations describe how two propositions relate to one another, and identifying them automatically is an integral part of natural language understanding. However, annotating discourse relations typically requires expert annotators. Recently, different semantic aspects of a sentence have been represented and crowd-sourced via question-and-answer (QA) pairs. This paper proposes a novel representation of discourse relations as QA pairs, which in turn allows us to crowd-source wide-coverage data annotated with discourse relations, via an intuitively appealing interface for composing such questions and answers. Based on our proposed representation, we collect a novel and wide-coverage QADiscourse dataset, and present baseline algorithms for predicting QADiscourse relations.

In standard NLP pipelines, morphological analysis and disambiguation (MA&D) precedes syntactic and semantic downstream tasks. However, for languages with complex and ambiguous word-internal structure, known as morphologically rich languages (MRLs), it has been hypothesized that syntactic context may be crucial for accurate MA&D, and vice versa. In this work we empirically confirm this hypothesis for Modern Hebrew, an MRL with complex morphology and severe word-level ambiguity, in a novel transition-based framework. Specifically, we propose a joint morphosyntactic transition-based framework which formally unifies two distinct transition systems, morphological and syntactic, into a single transition-based system with joint training and joint inference. We empirically show that MA&D results obtained in the joint settings outperform MA&D results obtained by the respective standalone components, and that end-to-end parsing results obtained by our joint system present a new state of the art for Hebrew dependency parsing.

Following navigation instructions in natural language (NL) requires a composition of language, action, and knowledge of the environment. Knowledge of the environment may be provided via visual sensors or as a symbolic world representation referred to as a map. Previous work on map-based NL navigation relied on small artificial worlds with a fixed set of entities known in advance. Here we introduce the Realistic Urban Navigation (RUN) task, aimed at interpreting NL navigation instructions based on a real, dense, urban map. Using Amazon Mechanical Turk, we collected a dataset of 2515 instructions aligned with actual routes over three regions of Manhattan. We then empirically study which aspects of a neural architecture are important for the RUN success, and empirically show that entity abstraction, attention over words and worlds, and a constantly updating world-state, significantly contribute to task accuracy.

For languages with simple morphology such as English, automatic annotation pipelines such as spaCy or Stanford’s CoreNLP successfully serve projects in academia and the industry. For many morphologically-rich languages (MRLs), similar pipelines show sub-optimal performance that limits their applicability for text analysis in research and the industry. The sub-optimal performance is mainly due to errors in early morphological disambiguation decisions, that cannot be recovered later on in the pipeline, yielding incoherent annotations on the whole. This paper describes the design and use of the ONLP suite, a joint morpho-syntactic infrastructure for processing Modern Hebrew texts. The joint inference over morphology and syntax substantially limits error propagation, and leads to high accuracy. ONLP provides rich and expressive annotations which already serve diverse academic and commercial needs. Its accompanying demo further serves educational activities, introducing Hebrew NLP intricacies to researchers and non-researchers alike.

We present the contribution of the ONLP lab at the Open University of Israel to the UD shared task on multilingual parsing from raw text to Universal Dependencies. Our contribution is based on a transition-based parser called ‘yap – yet another parser’, which includes a standalone morphological model, a standalone dependency model, and a joint morphosyntactic model. In the task we used yap‘s standalone dependency parser to parse input morphologically disambiguated by UDPipe, and obtained the official score of 58.35 LAS. In our follow up investigation we use yap to show how the incorporation of morphological and lexical resources may improve the performance of end-to-end raw-to-dependencies parsing in the case of a morphologically-rich and low-resource language, Modern Hebrew. Our results on Hebrew underscore the importance of CoNLL-UL, a UD-compatible standard for accessing external lexical resources, for enhancing end-to-end UD parsing, in particular for morphologically rich and low-resource languages. We thus encourage the community to create, convert, or make available more such lexica in future tasks.

This paper empirically studies the effects of representation choices on neural sentiment analysis for Modern Hebrew, a morphologically rich language (MRL) for which no sentiment analyzer currently exists. We study two dimensions of representational choices: (i) the granularity of the input signal (token-based vs. morpheme-based), and (ii) the level of encoding of vocabulary items (string-based vs. character-based). We hypothesise that for MRLs, languages where multiple meaning-bearing elements may be carried by a single space-delimited token, these choices will have measurable effects on task perfromance, and that these effects may vary for different architectural designs — fully-connected, convolutional or recurrent. Specifically, we hypothesize that morpheme-based representations will have advantages in terms of their generalization capacity and task accuracy, due to their better OOV coverage. To empirically study these effects, we develop a new sentiment analysis benchmark for Hebrew, based on 12K social media comments, and provide two instances of these data: in token-based and morpheme-based settings. Our experiments show that representation choices empirical effects vary with architecture type. While fully-connected and convolutional networks slightly prefer token-based settings, RNNs benefit from a morpheme-based representation, in accord with the hypothesis that explicit morphological information may help generalize. Our endeavour also delivers the first state-of-the-art broad-coverage sentiment analyzer for Hebrew, with over 89% accuracy, alongside an established benchmark to further study the effects of linguistic representation choices on neural networks’ task performance.

The Hebrew treebank (HTB), consisting of 6221 morpho-syntactically annotated newspaper sentences, has been the only resource for training and validating statistical parsers and taggers for Hebrew, for almost two decades now. During these decades, the HTB has gone through a trajectory of automatic and semi-automatic conversions, until arriving at its UDv2 form. In this work we manually validate the UDv2 version of the HTB, and, according to our findings, we apply scheme changes that bring the UD HTB to the same theoretical grounds as the rest of UD. Our experimental parsing results with UDv2New confirm that improving the coherence and internal consistency of the UD HTB indeed leads to improved parsing performance. At the same time, our analysis demonstrates that there is more to be done at the point of intersection of UD with other linguistic processing layers, in particular, at the points where UD interfaces external morphological and lexical resources.

We present the Open University’s submission to the CoNLL 2017 Shared Task on multilingual parsing from raw text to Universal Dependencies. The core of our system is a joint morphological disambiguator and syntactic parser which accepts morphologically analyzed surface tokens as input and returns morphologically disambiguated dependency trees as output. Our parser requires a lattice as input, so we generate morphological analyses of surface tokens using a data-driven morphological analyzer that derives its lexicon from the UD training corpora, and we rely on UDPipe for sentence segmentation and surface-level tokenization. We report our official macro-average LAS is 56.56. Although our model is not as performant as many others, it does not make use of neural networks, therefore we do not rely on word embeddings or any other data source other than the corpora themselves. In addition, we show the utility of a lexicon-backed morphological analyzer for the MRL Modern Hebrew. We use our results on Modern Hebrew to argue that the UD community should define a UD-compatible standard for access to lexical resources, which we argue is crucial for MRLs and low resource languages in particular.

Opinionated Natural Language Generation (ONLG) is a new, challenging, task that aims to automatically generate human-like, subjective, responses to opinionated articles online. We present a data-driven architecture for ONLG that generates subjective responses triggered by users’ agendas, consisting of topics and sentiments, and based on wide-coverage automatically-acquired generative grammars. We compare three types of grammatical representations that we design for ONLG, which interleave different layers of linguistic information and are induced from a new, enriched dataset we developed. Our evaluation shows that generation with Relational-Realizational (Tsarfaty and Sima’an, 2008) inspired grammar gets better language model scores than lexicalized grammars ‘a la Collins (2003), and that the latter gets better human-evaluation scores. We also show that conditioning the generation on topic models makes generated responses more relevant to the document content.

Cross-linguistically consistent annotation is necessary for sound comparative evaluation and cross-lingual learning experiments. It is also useful for multilingual system development and comparative linguistic studies. Universal Dependencies is an open community effort to create cross-linguistically consistent treebank annotation for many languages within a dependency-based lexicalist framework. In this paper, we describe v1 of the universal guidelines, the underlying design principles, and the currently available treebanks for 33 languages.

Parsing texts into universal dependencies (UD) in realistic scenarios requires infrastructure for the morphological analysis and disambiguation (MA&D) of typologically different languages as a first tier. MA&D is particularly challenging in morphologically rich languages (MRLs), where the ambiguous space-delimited tokens ought to be disambiguated with respect to their constituent morphemes, each morpheme carrying its own tag and a rich set features. Here we present a novel, language-agnostic, framework for MA&D, based on a transition system with two variants — word-based and morpheme-based — and a dedicated transition to mitigate the biases of variable-length morpheme sequences. Our experiments on a Modern Hebrew case study show state of the art results, and we show that the morpheme-based MD consistently outperforms our word-based variant. We further illustrate the utility and multilingual coverage of our framework by morphologically analyzing and disambiguating the large set of languages in the UD treebanks.

Morphologically rich languages pose a challenge to the annotators of treebanks with respect to the status of orthographic (space-delimited) words in the syntactic parse trees. In such languages an orthographic word may carry various, distinct, sorts of information and the question arises whether we should represent such words as a sequence of their constituent morphemes (i.e., a Morpheme-Based annotation strategy) or whether we should preserve their special orthographic status within the trees (i.e., a Word-Based annotation strategy). In this paper we empirically address this challenge in the context of the development of Language Resources for Modern Hebrew. We compare and contrast the Morpheme-Based and Word-Based annotation strategies of pronominal clitics in Modern Hebrew and we show that the Word-Based strategy is more adequate for the purpose of training statistical parsers as it provides a better PP-attachment disambiguation capacity and a better alignment with initial surface forms. Our findings in turn raise new questions concerning the interaction of morphological and syntactic processing of which investigation is facilitated by the parallel treebank we made available.