Large language models (LLMs) have been shown to propagate and amplify harmful stereotypes, particularly those that disproportionately affect marginalised communities. To understand the effect of these stereotypes more comprehensively, we introduce GlobalBias, a dataset of 876k sentences incorporating 40 distinct gender-by-ethnicity groups alongside descriptors typically used in bias literature, which enables us to study a broad set of stereotypes from around the world. We use GlobalBias to directly probe a suite of LMs via perplexity, which we use as a proxy to determine how certain stereotypes are represented in the model’s internal representations. Following this, we generate character profiles based on given names and evaluate the prevalence of stereotypes in model outputs. We find that the demographic groups associated with various stereotypes remain consistent across model likelihoods and model outputs. Furthermore, larger models consistently display higher levels of stereotypical outputs, even when explicitly instructed not to.

Hoaxes are a recognised form of disinformation created deliberately, with potential serious implications in the credibility of reference knowledge resources such as Wikipedia. What makes detecting Wikipedia hoaxes hard is that they often are written according to the official style guidelines. In this work, we first provide a systematic analysis of similarities and discrepancies between legitimate and hoax Wikipedia articles, and introduce HOAXPEDIA, a collection of 311 hoax articles (from existing literature and official Wikipedia lists), together with semantically similar legitimate articles, which together form a binary text classification dataset aimed at fostering research in automated hoax detection. In this paper, We report results after analyzing several language models, hoax-to-legit ratios, and the amount of text classifiers are exposed to (full article vs the article’s definition alone). Our results suggest that detecting deceitful content in Wikipedia based on content alone is hard but feasible, and complement our analysis with a study on the differences in distributions in edit histories, and find that looking at this feature yields better classification results than context.

We introduce RAGAs (Retrieval Augmented Generation Assessment), a framework for reference-free evaluation of Retrieval Augmented Generation (RAG) pipelines. RAGAs is available at [https://github.com/explodinggradients/ragas]. RAG systems are composed of a retrieval and an LLM based generation module. They provide LLMs with knowledge from a reference textual database, enabling them to act as a natural language layer between a user and textual databases, thus reducing the risk of hallucinations. Evaluating RAG architectures is challenging due to several dimensions to consider: the ability of the retrieval system to identify relevant and focused context passages, the ability of the LLM to exploit such passages faithfully, and the quality of the generation itself. With RAGAs, we introduce a suite of metrics that can evaluate these different dimensions without relying on ground truth human annotations. We posit that such a framework can contribute crucially to faster evaluation cycles of RAG architectures, which is especially important given the fast adoption of LLMs.

Contextualised Language Models (LM) improve on traditional word embeddings by encoding the meaning of words in context. However, such models have also made it possible to learn high-quality decontextualised concept embeddings. Three main strategies for learning such embeddings have thus far been considered: (i) fine-tuning the LM to directly predict concept embeddings from the name of the concept itself, (ii) averaging contextualised representations of mentions of the concept in a corpus, and (iii) encoding definitions of the concept. As these strategies have complementary strengths and weaknesses, we propose to learn a unified embedding space in which all three types of representations can be integrated. We show that this allows us to outperform existing approaches in tasks such as ontology completion, which heavily depends on access to high-quality concept embeddings. We furthermore find that mentions and definitions are well-aligned in the resulting space, enabling tasks such as target sense verification, even without the need for any fine-tuning.

Dictionary definitions play a prominent role in a wide range of NLP tasks, for instance by providing additional context about the meaning of rare and emerging terms. Many dictionaries also provide examples to illustrate the prototypical usage of words, which brings further opportunities for training or enriching NLP models. The intrinsic qualities of dictionaries, and related lexical resources such as glossaries and encyclopedias, are however still not well-understood. While there has been significant work on developing best practices, such guidance has been aimed at traditional usages of dictionaries (e.g. supporting language learners), and it is currently unclear how different quality aspects affect the NLP systems that rely on them. To address this issue, we compare WordNet, the most commonly used lexical resource in NLP, with a variety of dictionaries, as well as with examples that were generated by ChatGPT. Our analysis involves human judgments as well as automatic metrics. We furthermore study the quality of word embeddings derived from dictionary examples, as a proxy for downstream performance. We find that WordNet’s examples lead to lower-quality embeddings than those from the Oxford dictionary. Surprisingly, however, the ChatGPT generated examples were found to be most effective overall.

Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the community to know, for instance, given a task, which is the best performing model and how it compares with others. To alleviate this issue, we introduce a unified benchmark for NLP evaluation in social media, SuperTweetEval, which includes a heterogeneous set of tasks and datasets combined, adapted and constructed from scratch. We benchmarked the performance of a wide range of models on SuperTweetEval and our results suggest that, despite the recent advances in language modelling, social media remains challenging.

Metaphor identification aims at understanding whether a given expression is used figuratively in context. However, in this paper we show how existing metaphor identification datasets can be gamed by fully ignoring the potential metaphorical expression or the context in which it occurs. We test this hypothesis in a variety of datasets and settings, and show that metaphor identification systems based on language models without complete information can be competitive with those using the full context. This is due to the construction procedures to build such datasets, which introduce unwanted biases for positive and negative classes. Finally, we test the same hypothesis on datasets that are carefully sampled from natural corpora and where this bias is not present, making these datasets more challenging and reliable.

Concepts play a central role in many applications. This includes settings where concepts have to be modelled in the absence of sentence context. Previous work has therefore focused on distilling decontextualised concept embeddings from language models. But concepts can be modelled from different perspectives, whereas concept embeddings typically mostly capture taxonomic structure. To address this issue, we propose a strategy for identifying what different concepts, from a potentially large concept vocabulary, have in common with others. We then represent concepts in terms of the properties they share with the other concepts. To demonstrate the practical usefulness of this way of modelling concepts, we consider the task of ultra-fine entity typing, which is a challenging multi-label classification problem. We show that by augmenting the label set with shared properties, we can improve the performance of the state-of-the-art models for this task.

Definitions are a fundamental building block in lexicography, linguistics and computational semantics. In NLP, they have been used for retrofitting word embeddings or augmenting contextual representations in language models. However, lexical resources containing definitions exhibit a wide range of properties, which has implications in the behaviour of models trained and evaluated on them. In this paper, we introduce 3D-EX, a dataset that aims to fill this gap by combining well-known English resources into one centralized knowledge repository in the form of <term, definition, example> triples. 3D-EX is a unified evaluation framework with carefully pre-computed train/validation/test splits to prevent memorization. We report experimental results that suggest that this dataset could be effectively leveraged in downstream NLP tasks. Code and data are available at https://github.com/F-Almeman/3D-EX.

A fundamental challenge in the current NLP context, dominated by language models, comes from the inflexibility of current architectures to “learn” new information. While model-centric solutions like continual learning or parameter-efficient fine-tuning are available, the question still remains of how to reliably identify changes in language or in the world. In this paper, we propose WikiTiDe, a dataset derived from pairs of timestamped definitions extracted from Wikipedia. We argue that such resources can be helpful for accelerating diachronic NLP, specifically, for training models able to scan knowledge resources for core updates concerning a concept, an event, or a named entity. Our proposed end-to-end method is fully automatic and leverages a bootstrapping algorithm for gradually creating a high-quality dataset. Our results suggest that bootstrapping the seed version of WikiTiDe leads to better-fine-tuned models. We also leverage fine-tuned models in a number of downstream tasks, showing promising results with respect to competitive baselines.

Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual learning strategy contributes to enhancing Twitter-based language models’ capacity to deal with future and out-of-distribution tweets, while making them competitive with standardized and more monolithic benchmarks. We also perform a number of qualitative analyses showing how they cope with trends and peaks in activity involving specific named entities or concept drift. TimeLMs is available at github.com/cardiffnlp/timelms.

In this paper we present TweetNLP, an integrated platform for Natural Language Processing (NLP) in social media. TweetNLP supports a diverse set of NLP tasks, including generic focus areas such as sentiment analysis and named entity recognition, as well as social media-specific tasks such as emoji prediction and offensive language identification. Task-specific systems are powered by reasonably-sized Transformer-based language models specialized on social media text (in particular, Twitter) which can be run without the need for dedicated hardware or cloud services. The main contributions of TweetNLP are: (1) an integrated Python library for a modern toolkit supporting social media analysis using our various task-specific models adapted to the social domain; (2) an interactive online demo for codeless experimentation using our models; and (3) a tutorial covering a wide variety of typical social media applications.

Recognizing and categorizing lexical collocations in context is useful for language learning, dictionary compilation and downstream NLP. However, it is a challenging task due to the varying degrees of frozenness lexical collocations exhibit. In this paper, we put forward a sequence tagging BERT-based model enhanced with a graph-aware transformer architecture, which we evaluate on the task of collocation recognition in context. Our results suggest that explicitly encoding syntactic dependencies in the model architecture is helpful, and provide insights on differences in collocation typification in English, Spanish and French.

In this paper, we analyze zero-shot taxonomy learning methods which are based on distilling knowledge from language models via prompting and sentence scoring. We show that, despite their simplicity, these methods outperform some supervised strategies and are competitive with the current state-of-the-art under adequate conditions. We also show that statistical and linguistic properties of prompts dictate downstream performance.

Language models are ubiquitous in current NLP, and their multilingual capacity has recently attracted considerable attention. However, current analyses have almost exclusively focused on (multilingual variants of) standard benchmarks, and have relied on clean pre-training and task-specific corpora as multilingual signals. In this paper, we introduce XLM-T, a model to train and evaluate multilingual language models in Twitter. In this paper we provide: (1) a new strong multilingual baseline consisting of an XLM-R (Conneau et al. 2020) model pre-trained on millions of tweets in over thirty languages, alongside starter code to subsequently fine-tune on a target task; and (2) a set of unified sentiment analysis Twitter datasets in eight different languages and a XLM-T model trained on this dataset.

Many applications crucially rely on the availability of high-quality word vectors. To learn such representations, several strategies based on language models have been proposed in recent years. While effective, these methods typically rely on a large number of contextualised vectors for each word, which makes them impractical. In this paper, we investigate whether similar results can be obtained when only a few contextualised representations of each word can be used. To this end, we analyse a range of strategies for selecting the most informative sentences. Our results show that with a careful selection strategy, high-quality word vectors can be learned from as few as 5 to 10 sentences.

Patronizing and Condescending Language (PCL) is a subtle but harmful type of discourse, yet the task of recognizing PCL remains under-studied by the NLP community. Recognizing PCL is challenging because of its subtle nature, because available datasets are limited in size, and because this task often relies on some form of commonsense knowledge. In this paper, we study to what extent PCL detection models can be improved by pre-training them on other, more established NLP tasks. We find that performance gains are indeed possible in this way, in particular when pre-training on tasks focusing on sentiment, harmful language and commonsense morality. In contrast, for tasks focusing on political speech and social justice, no or only very small improvements were witnessed. These findings improve our understanding of the nature of PCL.

Definition modeling is the task to generate a valid definition for a given input term. This relatively novel task has been approached either with no context (i.e., given a word embedding alone) and, more recently, as word-in-context modeling. Despite their success, most works make little to no distinction between resources and their specific features (e.g., type and style of definitions, or quality of examples) when used for training. Given the high diversity lexicographic resources exhibit in terms of topic coverage, style and formal structure, it is desirable for downstream definition modeling to better understand which of them are better suited for the task. In this paper, we propose an empirical evaluation of the well-known lexical database WordNet, and specifically, its dictionary examples. We evaluate them both directly, by matching them against criteria for good dictionary writing, and indirectly, in the task of definition modeling. Our results suggest that WordNet’s dictionary examples could be improved by extending them in length, and incorporating prototypicality.

This paper describes the experiments ran for SemEval-2022 Task 2, subtask A, zero-shot and one-shot settings for idiomaticity detection. Our main approach is based on fine-tuning transformer-based language models as a baseline to perform binary classification. Our system, CardiffNLP-Metaphor, ranked 8th and 7th (respectively on zero- and one-shot settings on this task. Our main contribution lies in the extensive evaluation of transformer-based language models and various configurations, showing, among others, the potential of large multilingual models over base monolingual models. Moreover, we analyse the impact of various input parameters, which offer interesting insights on how language models work in practice.

This paper presents an overview of Task 4 at SemEval-2022, which was focused on detecting Patronizing and Condescending Language (PCL) towards vulnerable communities. Two sub-tasks were considered: a binary classification task, where participants needed to classify a given paragraph as containing PCL or not, and a multi-label classification task, where participants needed to identify which types of PCL are present (if any). The task attracted more than 300 participants, 77 teams and 229 valid submissions. We provide an overview of how the task was organized, discuss the techniques that were employed by the different participants, and summarize the main resulting insights about PCL detection and categorization.

Interpreting patient case descriptions has emerged as a challenging problem for biomedical NLP, where the aim is typically to predict diagnoses, to recommended treatments, or to answer questions about cases more generally. Previous work has found that biomedical language models often lack the knowledge that is needed for such tasks. In this paper, we aim to improve their performance through a self-supervised intermediate fine-tuning strategy based on PubMed abstracts. Our solution builds on the observation that many of these abstracts are case reports, and thus essentially patient case descriptions. As a general strategy, we propose to fine-tune biomedical language models on the task of predicting masked medical concepts from such abstracts. We find that the success of this strategy crucially depends on the selection of the medical concepts to be masked. By ensuring that these concepts are sufficiently salient, we can substantially boost the performance of biomedical language models, achieving state-of-the-art results on two benchmarks.

Language evolves over time, and word meaning changes accordingly. This is especially true in social media, since its dynamic nature leads to faster semantic shifts, making it challenging for NLP models to deal with new content and trends. However, the number of datasets and models that specifically address the dynamic nature of these social platforms is scarce. To bridge this gap, we present TempoWiC, a new benchmark especially aimed at accelerating research in social media-based meaning shift. Our results show that TempoWiC is a challenging benchmark, even for recently-released language models specialized in social media.

Grasping the commonsense properties of everyday concepts is an important prerequisite to language understanding. While contextualised language models are reportedly capable of predicting such commonsense properties with human-level accuracy, we argue that such results have been inflated because of the high similarity between training and test concepts. This means that models which capture concept similarity can perform well, even if they do not capture any knowledge of the commonsense properties themselves. In settings where there is no overlap between the properties that are considered during training and testing, we find that the empirical performance of standard language models drops dramatically. To address this, we study the possibility of fine-tuning language models to explicitly model concepts and their properties. In particular, we train separate concept and property encoders on two types of readily available data: extracted hyponym-hypernym pairs and generic sentences. Our experimental results show that the resulting encoders allow us to predict commonsense properties with much higher accuracy than is possible by directly fine-tuning language models. We also present experimental results for the related task of unsupervised hypernym discovery.

Analogies play a central role in human commonsense reasoning. The ability to recognize analogies such as “eye is to seeing what ear is to hearing”, sometimes referred to as analogical proportions, shape how we structure knowledge and understand language. Surprisingly, however, the task of identifying such analogies has not yet received much attention in the language model era. In this paper, we analyze the capabilities of transformer-based language models on this unsupervised task, using benchmarks obtained from educational settings, as well as more commonly used datasets. We find that off-the-shelf language models can identify analogies to a certain extent, but struggle with abstract and complex relations, and results are highly sensitive to model architecture and hyperparameters. Overall the best results were obtained with GPT-2 and RoBERTa, while configurations using BERT were not able to outperform word embedding models. Our results raise important questions for future work about how, and to what extent, pre-trained language models capture knowledge about abstract semantic relations.

One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that high-quality representations can be obtained by summarizing the sentence contexts of word mentions. In this paper, we propose a method for learning word representations that follows this basic strategy, but differs from standard word embeddings in two important ways. First, we take advantage of contextualized language models (CLMs) rather than bags of word vectors to encode contexts. Second, rather than learning a word vector directly, we use a topic model to partition the contexts in which words appear, and then learn different topic-specific vectors for each word. Finally, we use a task-specific supervision signal to make a soft selection of the resulting vectors. We show that this simple strategy leads to high-quality word vectors, which are more predictive of semantic properties than word embeddings and existing CLM-based strategies.

Lexical collocations are idiosyncratic combinations of two syntactically bound lexical items (e.g., “heavy rain” or “take a step”). Understanding their degree of compositionality and idiosyncrasy, as well their underlying semantics, is crucial for language learners, lexicographers and downstream NLP applications. In this paper, we perform an exhaustive analysis of current language models for collocation understanding. We first construct a dataset of apparitions of lexical collocations in context, categorized into 17 representative semantic categories. Then, we perform two experiments: (1) unsupervised collocate retrieval using BERT, and (2) supervised collocation classification in context. We find that most models perform well in distinguishing light verb constructions, especially if the collocation’s first argument acts as subject, but often fail to distinguish, first, different syntactic structures within the same semantic category, and second, fine-grained semantic categories which restrict the use of small sets of valid collocates for a given base.

In this paper, we introduce a new annotated dataset which is aimed at supporting the development of NLP models to identify and categorize language that is patronizing or condescending towards vulnerable communities (e.g. refugees, homeless people, poor families). While the prevalence of such language in the general media has long been shown to have harmful effects, it differs from other types of harmful language, in that it is generally used unconsciously and with good intentions. We furthermore believe that the often subtle nature of patronizing and condescending language (PCL) presents an interesting technical challenge for the NLP community. Our analysis of the proposed dataset shows that identifying PCL is hard for standard NLP models, with language models such as BERT achieving the best results.

Pre-trained neural language models (LMs) have achieved impressive results in various natural language processing tasks, across different languages. Surprisingly, this extends to the social media genre, despite the fact that social media often has very different characteristics from the language that LMs have seen during training. A particularly striking example is the performance of AraBERT, an LM for the Arabic language, which is successful in categorizing social media posts in Arabic dialects, despite only having been trained on Modern Standard Arabic. Our hypothesis in this paper is that the performance of LMs for social media can nonetheless be improved by incorporating static word vectors that have been specifically trained on social media. We show that a simple method for incorporating such word vectors is indeed successful in several Arabic and English benchmarks. Curiously, however, we also find that similar improvements are possible with word vectors that have been trained on traditional text sources (e.g. Wikipedia).

We describe the system submitted to SemEval-2020 Task 6, Subtask 1. The aim of this subtask is to predict whether a given sentence contains a definition or not. Unsurprisingly, we found that strong results can be achieved by fine-tuning a pre-trained BERT language model. In this paper, we analyze the performance of this strategy. Among others, we show that results can be improved by using a two-step fine-tuning process, in which the BERT model is first fine-tuned on the full training set, and then further specialized towards a target domain.

Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings by aligning monolingual spaces have shown that accurate alignments can be obtained with little or no supervision, which usually comes in the form of bilingual dictionaries. However, the focus has been on a particular controlled scenario for evaluation, and there is no strong evidence on how current state-of-the-art systems would fare with noisy text or for language pairs with major linguistic differences. In this paper we present an extensive evaluation over multiple cross-lingual embedding models, analyzing their strengths and limitations with respect to different variables such as target language, training corpora and amount of supervision. Our conclusions put in doubt the view that high-quality cross-lingual embeddings can always be learned without much supervision.

Textual definitions constitute a fundamental source of knowledge when seeking the meaning of words, and they are the cornerstone of lexical resources like glossaries, dictionaries, encyclopedia or thesauri. In this paper, we present an in-depth analytical study on the main features relevant to the task of definition extraction. Our main goal is to study whether linguistic structures from canonical (the Aristotelian or genus et differentia model) can be leveraged to retrieve definitions from corpora in different domains of knowledge and textual genres alike. To this end, we develop a simple linear classifier and analyze the contribution of several (sets of) linguistic features. Finally, as a result of our experiments, we also shed light on the particularities of existing benchmarks as well as the most challenging aspects of the task.

Depression and anxiety are psychiatric disorders that are observed in many areas of everyday life. For example, these disorders manifest themselves somewhat frequently in texts written by nondiagnosed users in social media. However, detecting users with these conditions is not a straightforward task as they may not explicitly talk about their mental state, and if they do, contextual cues such as immediacy must be taken into account. When available, linguistic flags pointing to probable anxiety or depression could be used by medical experts to write better guidelines and treatments. In this paper, we develop a dataset designed to foster research in depression and anxiety detection in Twitter, framing the detection task as a binary tweet classification problem. We then apply state-of-the-art classification models to this dataset, providing a competitive set of baselines alongside qualitative error analysis. Our results show that language models perform reasonably well, and better than more traditional baselines. Nonetheless, there is clear room for improvement, particularly with unbalanced training sets and in cases where seemingly obvious linguistic cues (keywords) are used counter-intuitively.

The experimental landscape in natural language processing for social media is too fragmented. Each year, new shared tasks and datasets are proposed, ranging from classics like sentiment analysis to irony detection or emoji prediction. Therefore, it is unclear what the current state of the art is, as there is no standardized evaluation protocol, neither a strong set of baselines trained on such domain-specific data. In this paper, we propose a new evaluation framework (TweetEval) consisting of seven heterogeneous Twitter-specific classification tasks. We also provide a strong set of baselines as starting point, and compare different language modeling pre-training strategies. Our initial experiments show the effectiveness of starting off with existing pre-trained generic language models, and continue training them on Twitter corpora.

Collocations in the sense of idiosyncratic lexical co-occurrences of two syntactically bound words traditionally pose a challenge to language learners and many Natural Language Processing (NLP) applications alike. Reliable ground truth (i.e., ideally manually compiled) resources are thus of high value. We present a manually compiled bilingual English–French collocation resource with 7,480 collocations in English and 6,733 in French. Each collocation is enriched with information that facilitates its downstream exploitation in NLP tasks such as machine translation, word sense disambiguation, natural language generation, relation classification, and so forth. Our proposed enrichment covers: the semantic category of the collocation (its lexical function), its vector space representation (for each individual word as well as their joint collocation embedding), a subcategorization pattern of both its elements, as well as their corresponding BabelNet id, and finally, indices of their occurrences in large scale reference corpora.

This paper summarizes our contribution to the Hyperpartisan News Detection task in SemEval 2019. We experiment with two different approaches: 1) an SVM classifier based on word vector averages and hand-crafted linguistic features, and 2) a BiLSTM-based neural text classifier trained on a filtered training set. Surprisingly, despite their different nature, both approaches achieve an accuracy of 0.74. The main focus of this paper is to further analyze the remarkable fact that a simple feature-based approach can perform on par with modern neural classifiers. We also highlight the effectiveness of our filtering strategy for training the neural network on a large but noisy training set.

While word embeddings have been shown to implicitly encode various forms of attributional knowledge, the extent to which they capture relational information is far more limited. In previous work, this limitation has been addressed by incorporating relational knowledge from external knowledge bases when learning the word embedding. Such strategies may not be optimal, however, as they are limited by the coverage of available resources and conflate similarity with other forms of relatedness. As an alternative, in this paper we propose to encode relational knowledge in a separate word embedding, which is aimed to be complementary to a given standard word embedding. This relational word embedding is still learned from co-occurrence statistics, and can thus be used even when no external knowledge base is available. Our analysis shows that relational word vectors do indeed capture information that is complementary to what is encoded in standard word embeddings.

Lexical relation classification is the task of predicting whether a certain relation holds between a given pair of words. In this paper, we explore to which extent the current distributional landscape based on word embeddings provides a suitable basis for classification of collocations, i.e., pairs of words between which idiosyncratic lexical relations hold. First, we introduce a novel dataset with collocations categorized according to lexical functions. Second, we conduct experiments on a subset of this benchmark, comparing it in particular to the well known DiffVec dataset. In these experiments, in addition to simple word vector arithmetic operations, we also investigate the role of unsupervised relation vectors as a complementary input. While these relation vectors indeed help, we also show that lexical function classification poses a greater challenge than the syntactic and semantic relations that are typically used for benchmarks in the literature.

Automatically identifying definitional knowledge in text corpora (Definition Extraction or DE) is an important task with direct applications in, among others, Automatic Glossary Generation, Taxonomy Learning, Question Answering and Semantic Search. It is generally cast as a binary classification problem between definitional and non-definitional sentences. In this paper we present a set of neural architectures combining Convolutional and Recurrent Neural Networks, which are further enriched by incorporating linguistic information via syntactic dependencies. Our experimental results in the task of sentence classification, on two benchmarking DE datasets (one generic, one domain-specific), show that these models obtain consistent state of the art results. Furthermore, we demonstrate that models trained on clean Wikipedia-like definitions can successfully be applied to more noisy domain-specific corpora.

Incorporating linguistic, world and common sense knowledge into AI/NLP systems is currently an important research area, with several open problems and challenges. At the same time, processing and storing this knowledge in lexical resources is not a straightforward task. We propose to address these complementary goals from two methodological perspectives: the use of NLP methods to help the process of constructing and enriching lexical resources and the use of lexical resources for improving NLP applications. This tutorial may be useful for two main types of audience: those working on language resources who are interested in becoming acquainted with automatic NLP techniques, with the end goal of speeding and/or easing up the process of resource curation; and on the other hand, researchers in NLP who would like to benefit from the knowledge of lexical resources to improve their systems and models.

We present SeVeN (Semantic Vector Networks), a hybrid resource that encodes relationships between words in the form of a graph. Different from traditional semantic networks, these relations are represented as vectors in a continuous vector space. We propose a simple pipeline for learning such relation vectors, which is based on word vector averaging in combination with an ad hoc autoencoder. We show that by explicitly encoding relational information in a dedicated vector space we can capture aspects of word meaning that are complementary to what is captured by word embeddings. For example, by examining clusters of relation vectors, we observe that relational similarities can be identified at a more abstract level than with traditional word vector differences. Finally, we test the effectiveness of semantic vector networks in two tasks: measuring word similarity and neural text categorization. SeVeN is available at bitbucket.org/luisespinosa/seven.

Cross-lingual word embeddings are becoming increasingly important in multilingual NLP. Recently, it has been shown that these embeddings can be effectively learned by aligning two disjoint monolingual vector spaces through linear transformations, using no more than a small bilingual dictionary as supervision. In this work, we propose to apply an additional transformation after the initial alignment step, which moves cross-lingual synonyms towards a middle point between them. By applying this transformation our aim is to obtain a better cross-lingual integration of the vector spaces. In addition, and perhaps surprisingly, the monolingual spaces also improve by this transformation. This is in contrast to the original alignment, which is typically learned such that the structure of the monolingual spaces is preserved. Our experiments confirm that the resulting cross-lingual embeddings outperform state-of-the-art models in both monolingual and cross-lingual evaluation tasks.

Human language has evolved towards newer forms of communication such as social media, where emojis (i.e., ideograms bearing a visual meaning) play a key role. While there is an increasing body of work aimed at the computational modeling of emoji semantics, there is currently little understanding about what makes a computational model represent or predict a given emoji in a certain way. In this paper we propose a label-wise attention mechanism with which we attempt to better understand the nuances underlying emoji prediction. In addition to advantages in terms of interpretability, we show that our proposed architecture improves over standard baselines in emoji prediction, and does particularly well when predicting infrequent emojis.

This paper describes the results of the first Shared Task on Multilingual Emoji Prediction, organized as part of SemEval 2018. Given the text of a tweet, the task consists of predicting the most likely emoji to be used along such tweet. Two subtasks were proposed, one for English and one for Spanish, and participants were allowed to submit a system run to one or both subtasks. In total, 49 teams participated to the English subtask and 22 teams submitted a system run to the Spanish subtask. Evaluation was carried out emoji-wise, and the final ranking was based on macro F-Score. Data and further information about this task can be found at https://competitions.codalab.org/competitions/17344.

This paper describes the SemEval 2018 Shared Task on Hypernym Discovery. We put forward this task as a complementary benchmark for modeling hypernymy, a problem which has traditionally been cast as a binary classification task, taking a pair of candidate words as input. Instead, our reformulated task is defined as follows: given an input term, retrieve (or discover) its suitable hypernyms from a target corpus. We proposed five different subtasks covering three languages (English, Spanish, and Italian), and two specific domains of knowledge in English (Medical and Music). Participants were allowed to compete in any or all of the subtasks. Overall, a total of 11 teams participated, with a total of 39 different systems submitted through all subtasks. Data, results and further information about the task can be found at https://competitions.codalab.org/competitions/17119.

Videogame streaming platforms have become a paramount example of noisy user-generated text. These are websites where gaming is broadcasted, and allows interaction with viewers via integrated chatrooms. Probably the best known platform of this kind is Twitch, which has more than 100 million monthly viewers. Despite these numbers, and unlike other platforms featuring short messages (e.g. Twitter), Twitch has not received much attention from the Natural Language Processing community. In this paper we aim at bridging this gap by proposing two important tasks specific to the Twitch platform, namely (1) Emote prediction; and (2) Trolling detection. In our experiments, we evaluate three models: a BOW baseline, a logistic supervised classifiers based on word embeddings, and a bidirectional long short-term memory recurrent neural network (LSTM). Our results show that the LSTM model outperforms the other two models, where explicit features with proven effectiveness for similar tasks were encoded.

Collocations such as “heavy rain” or “make [a] decision”, are combinations of two elements where one (the base) is freely chosen, while the choice of the other (collocate) is restricted, depending on the base. Collocations present difficulties even to advanced language learners, who usually struggle to find the right collocate to express a particular meaning, e.g., both “heavy” and “strong” express the meaning ‘intense’, but while “rain” selects “heavy”, “wind” selects “strong”. Lexical Functions (LFs) describe the meanings that hold between the elements of collocations, such as ‘intense’, ‘perform’, ‘create’, ‘increase’, etc. Language resources with semantically classified collocations would be of great help for students, however they are expensive to build, since they are manually constructed, and scarce. We present an unsupervised approach to the acquisition and semantic classification of collocations according to LFs, based on word embeddings in which, given an example of a collocation for each of the target LFs and a set of bases, the system retrieves a list of collocates for each base and LF.

In this paper we present a gold standard dataset for Entity Linking (EL) in the Music Domain. It contains thousands of musical named entities such as Artist, Song or Record Label, which have been automatically annotated on a set of artist biographies coming from the Music website and social network Last.fm. The annotation process relies on the analysis of the hyperlinks present in the source texts and in a voting-based algorithm for EL, which considers, for each entity mention in text, the degree of agreement across three state-of-the-art EL systems. Manual evaluation shows that EL Precision is at least 94%, and due to its tunable nature, it is possible to derive annotations favouring higher Precision or Recall, at will. We make available the annotated dataset along with evaluation data and the code.

WordNet is probably the best known lexical resource in Natural Language Processing. While it is widely regarded as a high quality repository of concepts and semantic relations, updating and extending it manually is costly. One important type of relation which could potentially add enormous value to WordNet is the inclusion of collocational information, which is paramount in tasks such as Machine Translation, Natural Language Generation and Second Language Learning. In this paper, we present ColWordNet (CWN), an extended WordNet version with fine-grained collocational information, automatically introduced thanks to a method exploiting linear relations between analogous sense-level embeddings spaces. We perform both intrinsic and extrinsic evaluations, and release CWN for the use and scrutiny of the community.