This paper presents the objectives, organization and activities of the UniDive COST Action, a scientific network dedicated to universality, diversity and idiosyncrasy in language technology. We describe the objectives and organization of this initiative, the people involved, the working groups and the ongoing tasks and activities. This paper is also an pen call for participation towards new members and countries.

While static word embeddings are blind to context, for lexical semantics tasks context is rather too present in contextual word embeddings, vectors of same-meaning occurrences being too different (Ethayarajh, 2019). Fine-tuning pre-trained language models (PLMs) using contrastive learning was proposed, leveraging automatically self-augmented examples (Liu et al., 2021b). In this paper, we investigate how to inject a lexicon as an alternative source of supervision, using the English Wiktionary. We also test how dimensionality reduction impacts the resulting contextual word embeddings. We evaluate our approach on the Word-In-Context (WiC) task, in the unsupervised setting (not using the training set). We achieve new SoTA result on the original WiC test set. We also propose two new WiC test sets for which we show that our fine-tuning method achieves substantial improvements. We also observe improvements, although modest, for the semantic frame induction task. Although we experimented on English to allow comparison with related work, our method is adaptable to the many languages for which large Wiktionaries exist.

We present version 1.3 of the PARSEME multilingual corpus annotated with verbal multiword expressions. Since the previous version, new languages have joined the undertaking of creating such a resource, some of the already existing corpora have been enriched with new annotated texts, while others have been enhanced in various ways. The PARSEME multilingual corpus represents 26 languages now. All monolingual corpora therein use Universal Dependencies v.2 tagset. They are (re-)split observing the PARSEME v.1.2 standard, which puts impact on unseen VMWEs. With the current iteration, the corpus release process has been detached from shared tasks; instead, a process for continuous improvement and systematic releases has been introduced.

Multiword expression (MWE) identification has been the focus of numerous research papers, especially in the context of the DiMSUM and PARSEME Shared Tasks (STs). This survey analyses 40 MWE identification papers with experiments on data from these STs. We look at corpus selection, pre- and post-processing, MWE encoding, evaluation metrics, statistical significance, and error analyses. We find that these aspects are usually considered minor and/or omitted in the literature. However, they may considerably impact the results and the conclusions drawn from them. Therefore, we advocate for more systematic descriptions of experimental conditions to reduce the risk of misleading conclusions drawn from poorly designed experimental setup.

Multiword expressions (MWEs) are challenging and pervasive phenomena whose idiosyncratic properties show notably at the levels of lexicon, morphology, and syntax. Thus, they should best be annotated jointly with morphosyntax. We discuss two multilingual initiatives, Universal Dependencies and PARSEME, addressing these annotation layers in cross-lingually unified ways. We compare the annotation principles of these initiatives with respect to MWEs, and we put forward a roadmap towards their gradual unification. The expected outcomes are more consistent treebanking and higher universality in modeling idiosyncrasy.

Multiword expression (MWE) identification in tweets is a complex task due to the complex linguistic nature of MWEs combined with the non-standard language use in social networks. MWE features were shown to be helpful for hate speech detection (HSD). In this article, we present joint experiments on these two related tasks on English Twitter data: first we focus on the MWE identification task, and then we observe the influence of MWE-based features on the HSD task. For MWE identification, we compare the performance of two systems: lexicon-based and deep neural networks-based (DNN). We experimentally evaluate seven configurations of a state-of-the-art DNN system based on recurrent networks using pre-trained contextual embeddings from BERT. The DNN-based system outperforms the lexicon-based one thanks to its superior generalisation power, yielding much better recall. For the HSD task, we propose a new DNN architecture for incorporating MWE features. We confirm that MWE features are helpful for the HSD task. Moreover, the proposed DNN architecture beats previous MWE-based HSD systems by 0.4 to 1.1 F-measure points on average on four Twitter HSD corpora.

L’identification des expressions polylexicales (EP) dans les tweets est une tâche difficile en raison de la nature linguistique complexe des EP combinée à l’utilisation d’un langage non standard. Dans cet article, nous présentons cette tâche d’identification sur des données anglaises de Twitter. Nous comparons les performances de deux systèmes : un utilisant un dictionnaire et un autre des réseaux de neurones. Nous évaluons expérimentalement sept configurations d’un système état de l’art fondé sur des réseaux neuronaux récurrents utilisant des embeddings contextuels générés par BERT. Le système fondé sur les réseaux neuronaux surpasse l’approche dictionnaire, collecté automatiquement à partir des EP dans des corpus, grâce à son pouvoir de généralisation supérieur.

This paper introduces the mwetoolkit-lib, an adaptation of the mwetoolkit as a python library. The original toolkit performs the extraction and identification of multiword expressions (MWEs) in large text bases through the command line. One of the contributions of our work is the adaptation of the MWE extraction pipeline from the mwetoolkit, allowing its usage in python development environments and integration in larger pipelines. The other contribution is the execution of a pilot experiment aiming to show the impact of MWE discovery in data professionals’ work. This experiment found that the addition of MWE knowledge to the Term Frequency-Inverse Document Frequency (TF-IDF) vectorization altered the word relevance order, improving the linguistic quality of the clusters returned by k-means method.

This paper explains our participation in task 1 of the CASE 2021 shared task. This task is about multilingual event extraction from news. We focused on sub-task 4, event information extraction. This sub-task has a small training dataset and we fine-tuned a multilingual BERT to solve this sub-task. We studied the instability problem on the dataset and tried to mitigate it.

Automatic identification of multiword expressions (MWEs), like ‘to cut corners’ (to do an incomplete job), is a pre-requisite for semantically-oriented downstream applications. This task is challenging because MWEs, especially verbal ones (VMWEs), exhibit surface variability. This paper deals with a subproblem of VMWE identification: the identification of occurrences of previously seen VMWEs. A simple language-independent system based on a combination of filters competes with the best systems from a recent shared task: it obtains the best averaged F-score over 11 languages (0.6653) and even the best score for both seen and unseen VMWEs due to the high proportion of seen VMWEs in texts. This highlights the fact that focusing on the identification of seen VMWEs could be a strategy to improve VMWE identification in general.

Contextualised embeddings such as BERT have become de facto state-of-the-art references in many NLP applications, thanks to their impressive performances. However, their opaqueness makes it hard to interpret their behaviour. SLICE is a hybrid model that combines supersense labels with contextual embeddings. We introduce a weakly supervised method to learn interpretable embeddings from raw corpora and small lists of seed words. Our model is able to represent both a word and its context as embeddings into the same compact space, whose dimensions correspond to interpretable supersenses. We assess the model in a task of supersense tagging for French nouns. The little amount of supervision required makes it particularly well suited for low-resourced scenarios. Thanks to its interpretability, we perform linguistic analyses about the predicted supersenses in terms of input word and context representations.

We present edition 1.2 of the PARSEME shared task on identification of verbal multiword expressions (VMWEs). Lessons learned from previous editions indicate that VMWEs have low ambiguity, and that the major challenge lies in identifying test instances never seen in the training data. Therefore, this edition focuses on unseen VMWEs. We have split annotated corpora so that the test corpora contain around 300 unseen VMWEs, and we provide non-annotated raw corpora to be used by complementary discovery methods. We released annotated and raw corpora in 14 languages, and this semi-supervised challenge attracted 7 teams who submitted 9 system results. This paper describes the effort of corpus creation, the task design, and the results obtained by the participating systems, especially their performance on unseen expressions.

We describe the Seen2Unseen system that participated in edition 1.2 of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs). The identification of VMWEs that do not appear in the provided training corpora (called unseen VMWEs) – with a focus here on verb-noun VMWEs – is based on mutual information and lexical substitution or translation of seen VMWEs. We present the architecture of the system, report results for 14 languages, and propose an error analysis.

Translating biomedical ontologies is an important challenge, but doing it manually requires much time and money. We study the possibility to use open-source knowledge bases to translate biomedical ontologies. We focus on two aspects: coverage and quality. We look at the coverage of two biomedical ontologies focusing on diseases with respect to Wikidata for 9 European languages (Czech, Dutch, English, French, German, Italian, Polish, Portuguese and Spanish) for both, plus Arabic, Chinese and Russian for the second. We first use direct links between Wikidata and the studied ontologies and then use second-order links by going through other intermediate ontologies. We then compare the quality of the translations obtained thanks to Wikidata with a commercial machine translation tool, here Google Cloud Translation.

The existence of universal models to describe the syntax of languages has been debated for decades. The availability of resources such as the Universal Dependencies treebanks and the World Atlas of Language Structures make it possible to study the plausibility of universal grammar from the perspective of dependency parsing. Our work investigates the use of high-level language descriptions in the form of typological features for multilingual dependency parsing. Our experiments on multilingual parsing for 40 languages show that typological information can indeed guide parsers to share information between similar languages beyond simple language identification.

Nominal compounds such as red wine and nut case display a continuum of compositionality, with varying contributions from the components of the compound to its semantics. This article proposes a framework for compound compositionality prediction using distributional semantic models, evaluating to what extent they capture idiomaticity compared to human judgments. For evaluation, we introduce data sets containing human judgments in three languages: English, French, and Portuguese. The results obtained reveal a high agreement between the models and human predictions, suggesting that they are able to incorporate information about idiomaticity. We also present an in-depth evaluation of various factors that can affect prediction, such as model and corpus parameters and compositionality operations. General crosslingual analyses reveal the impact of morphological variation and corpus size in the ability of the model to predict compositionality, and of a uniform combination of the components for best results.

Because most multiword expressions (MWEs), especially verbal ones, are semantically non-compositional, their automatic identification in running text is a prerequisite for semantically-oriented downstream applications. However, recent developments, driven notably by the PARSEME shared task on automatic identification of verbal MWEs, show that this task is harder than related tasks, despite recent contributions both in multilingual corpus annotation and in computational models. In this paper, we analyse possible reasons for this state of affairs. They lie in the nature of the MWE phenomenon, as well as in its distributional properties. We also offer a comparative analysis of the state-of-the-art systems, which exhibit particularly strong sensitivity to unseen data. On this basis, we claim that, in order to make strong headway in MWE identification, the community should bend its mind into coupling identification of MWEs with their discovery, via syntactic MWE lexicons. Such lexicons need not necessarily achieve a linguistically complete modelling of MWEs’ behavior, but they should provide minimal morphosyntactic information to cover some potential uses, so as to complement existing MWE-annotated corpora. We define requirements for such minimal NLP-oriented lexicon, and we propose a roadmap for the MWE community driven by these requirements.

Recent initiatives such as the PARSEME shared task allowed the rapid development of MWE identification systems. Many of those are based on recent NLP advances, using neural sequence models that take continuous word representations as input. We study two related questions in neural MWE identification: (a) the use of lemmas and/or surface forms as input features, and (b) the use of word-based or character-based embeddings to represent them. Our experiments on Basque, French, and Polish show that character-based representations yield systematically better results than word-based ones. In some cases, character-based representations of surface forms can be used as a proxy for lemmas, depending on the morphological complexity of the language.

One of the most outstanding properties of multiword expressions (MWEs), especially verbal ones (VMWEs), important both in theoretical models and applications, is their idiosyncratic variability. Some MWEs are always continuous, while some others admit certain types of insertions. Components of some MWEs are rarely or never modified, while some others admit either specific or unrestricted modification. This unpredictable variability profile of MWEs hinders modeling and processing them as “words-with-spaces” on the one hand, and as regular syntactic structures on the other hand. Since variability of MWEs is a matter of scale rather than a binary property, we propose a 2-dimensional language-independent measure of variability dedicated to verbal MWEs based on syntactic and discontinuity-related clues. We assess its relevance with respect to a linguistic benchmark and its utility for the tasks of VMWE classification and variant identification on a French corpus.

Multiword expressions, especially verbal ones (VMWEs), show idiosyncratic variability, which is challenging for NLP applications, hence the need for VMWE identification. We focus on the task of variant identification, i.e. identifying variants of previously seen VMWEs, whatever their surface form. We model the problem as a classification task. Syntactic subtrees with previously seen combinations of lemmas are first extracted, and then classified on the basis of features relevant to morpho-syntactic variation of VMWEs. Feature values are both absolute, i.e. hold for a particular VMWE candidate, and relative, i.e. based on comparing a candidate with previously seen VMWEs. This approach outperforms a baseline by 4 percent points of F-measure on a French corpus.

This paper describes the PARSEME Shared Task 1.1 on automatic identification of verbal multiword expressions. We present the annotation methodology, focusing on changes from last year’s shared task. Novel aspects include enhanced annotation guidelines, additional annotated data for most languages, corpora for some new languages, and new evaluation settings. Corpora were created for 20 languages, which are also briefly discussed. We report organizational principles behind the shared task and the evaluation metrics employed for ranking. The 17 participating systems, their methods and obtained results are also presented and analysed.

We describe the VarIDE system (standing for Variant IDEntification) which participated in the edition 1.1 of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs). Our system focuses on the task of VMWE variant identification by using morphosyntactic information in the training data to predict if candidates extracted from the test corpus could be idiomatic, thanks to a naive Bayes classifier. We report results for 19 languages.

This paper describes the Veyn system, submitted to the closed track of the PARSEME Shared Task 2018 on automatic identification of verbal multiword expressions (VMWEs). Veyn is based on a sequence tagger using recurrent neural networks. We represent VMWEs using a variant of the begin-inside-outside encoding scheme combined with the VMWE category tag. In addition to the system description, we present development experiments to determine the best tagging scheme. Veyn is freely available, covers 19 languages, and was ranked ninth (MWE-based) and eight (Token-based) among 13 submissions, considering macro-averaged F1 across languages.

Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word boundaries that are both idiosyncratic and pervasive across different languages. The structure of linguistic processing that depends on the clear distinction between words and phrases has to be re-thought to accommodate MWEs. The issue of MWE handling is crucial for NLP applications, where it raises a number of challenges. The emergence of solutions in the absence of guiding principles motivates this survey, whose aim is not only to provide a focused review of MWE processing, but also to clarify the nature of interactions between MWE processing and downstream applications. We propose a conceptual framework within which challenges and research contributions can be positioned. It offers a shared understanding of what is meant by “MWE processing,” distinguishing the subtasks of MWE discovery and identification. It also elucidates the interactions between MWE processing and two use cases: Parsing and machine translation. Many of the approaches in the literature can be differentiated according to how MWE processing is timed with respect to underlying use cases. We discuss how such orchestration choices affect the scope of MWE-aware systems. For each of the two MWE processing subtasks and for each of the two use cases, we conclude on open issues and research perspectives.

Multiword expressions (MWEs) are known as a “pain in the neck” for NLP due to their idiosyncratic behaviour. While some categories of MWEs have been addressed by many studies, verbal MWEs (VMWEs), such as to take a decision, to break one’s heart or to turn off, have been rarely modelled. This is notably due to their syntactic variability, which hinders treating them as “words with spaces”. We describe an initiative meant to bring about substantial progress in understanding, modelling and processing VMWEs. It is a joint effort, carried out within a European research network, to elaborate universal terminologies and annotation guidelines for 18 languages. Its main outcome is a multilingual 5-million-word annotated corpus which underlies a shared task on automatic identification of VMWEs. This paper presents the corpus annotation methodology and outcome, the shared task organisation and the results of the participating systems.

We propose a method for joint unsupervised discovery of multiword expressions (MWEs) and their translations from parallel corpora. First, we apply independent monolingual MWE extraction in source and target languages simultaneously. Then, we calculate translation probability, association score and distributional similarity of co-occurring pairs. Finally, we rank all translations of a given MWE using a linear combination of these features. Preliminary experiments on light verb constructions show promising results.

We present a simple and efficient tagger capable of identifying highly ambiguous multiword expressions (MWEs) in French texts. It is based on conditional random fields (CRF), using local context information as features. We show that this approach can obtain results that, in some cases, approach more sophisticated parser-based MWE identification methods without requiring syntactic trees from a treebank. Moreover, we study how well the CRF can take into account external information coming from a lexicon.

Nous décrivons la partie française des données produites dans le cadre de la campagne multilingue PARSEME sur l’identification d’expressions polylexicales verbales (Savary et al., 2017). Les expressions couvertes pour le français sont les expressions verbales idiomatiques, les verbes intrinsèquement pronominaux et une généralisation des constructions à verbe support. Ces phénomènes ont été annotés sur le corpus French-UD (Nivre et al., 2016) et le corpus Sequoia (Candito & Seddah, 2012), soit un corpus de 22 645 phrases, pour un total de 4 962 expressions annotées. On obtient un ratio d’une expression annotée tous les 100 tokens environ, avec un fort taux d’expressions discontinues (40%).

This paper presents mwetoolkit+sem: an extension of the mwetoolkit that estimates semantic compositionality scores for multiword expressions (MWEs) based on word embeddings. First, we describe our implementation of vector-space operations working on distributional vectors. The compositionality score is based on the cosine distance between the MWE vector and the composition of the vectors of its member words. Our generic system can handle several types of word embeddings and MWE lists, and may combine individual word representations using several composition techniques. We evaluate our implementation on a dataset of 1042 English noun compounds, comparing different configurations of the underlying word embeddings and word-composition models. We show that our vector-based scores model non-compositionality better than standard association measures such as log-likelihood.

We introduce DeQue, a lexicon covering French complex prepositions (CPRE) like “à partir de” (from) and complex conjunctions (CCONJ) like “bien que” (although). The lexicon includes fine-grained linguistic description based on empirical evidence. We describe the general characteristics of CPRE and CCONJ in French, with special focus on syntactic ambiguity. Then, we list the selection criteria used to build the lexicon and the corpus-based methodology employed to collect entries. Finally, we quantify the ambiguity of each construction by annotating around 100 sentences randomly taken from the FRWaC. In addition to its theoretical value, the resource has many potential practical applications. We intend to employ DeQue for treebank annotation and to train a dependency parser that can takes complex constructions into account.

Comparable corpora have been used as an alternative for parallel corpora as resources for computational tasks that involve domain-specific natural language processing. One way to gather documents related to a specific topic of interest is to traverse a portion of the web graph in a targeted way, using focused crawling algorithms. In this paper, we compare several focused crawling algorithms using them to collect comparable corpora on a specific domain. Then, we compare the evaluation of the focused crawling algorithms to the performance of linguistic processes executed after training with the corresponding generated corpora. Also, we propose a novel approach for focused crawling, exploiting the expressive power of multiword expressions.

Distributional thesauri have been applied for a variety of tasks involving semantic relatedness. In this paper, we investigate the impact of three parameters: similarity measures, frequency thresholds and association scores. We focus on the robustness and stability of the resulting thesauri, measuring inter-thesaurus agreement when testing different parameter values. The results obtained show that low-frequency thresholds affect thesaurus quality more than similarity measures, with more agreement found for increasing thresholds. These results indicate the sensitivity of distributional thesauri to frequency. Nonetheless, the observed differences do not transpose over extrinsic evaluation using TOEFL-like questions. While this may be specific to the task, we argue that a careful examination of the stability of distributional resources prior to application is needed.

This paper presents the Multiword Expression Toolkit (mwetoolkit), an environment for type and language-independent MWE identification from corpora. The mwetoolkit provides a targeted list of MWE candidates, extracted and filtered according to a number of user-defined criteria and a set of standard statistical association measures. For generating corpus counts, the toolkit provides both a corpus indexation facility and a tool for integration with web search engines, while for evaluation, it provides validation and annotation facilities. The mwetoolkit also allows easy integration with a machine learning tool for the creation and application of supervised MWE extraction models if annotated data is available. In our experiment, the mwetoolkit was tested and evaluated in the context of MWE extraction in the biomedical domain. Our preliminary results show that the toolkit performs better than other approaches, especially concerning recall. Moreover, this first version can also be extended in several ways in order to improve the quality of the results.