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.

Contradictory results about the encoding of the semantic impact of negation in pretrained language models (PLMs) have been drawn recently (e.g. Kassner and Schütze (2020); Gubelmann and Handschuh (2022)).In this paper we focus rather on the way PLMs encode negation and its formal impact, through the phenomenon of the Negative Polarity Item (NPI) licensing in English.More precisely, we use probes to identify which contextual representations best encode 1) the presence of negation in a sentence, and 2) the polarity of a neighboring masked polarity item. We find that contextual representations of tokens inside the negation scope do allow for (i) a better prediction of the presence of “not” compared to those outside the scope and (ii) a better prediction of the right polarity of a masked polarity item licensed by “not”, although the magnitude of the difference varies from PLM to PLM. Importantly, in both cases the trend holds even when controlling for distance to “not”.This tends to indicate that the embeddings of these models do reflect the notion of negation scope, and do encode the impact of negation on NPI licensing. Yet, further control experiments reveal that the presence of other lexical items is also better captured when using the contextual representation of a token within the same syntactic clause than outside from it, suggesting that PLMs simply capture the more general notion of syntactic clause.

Several methodologies have recently been proposed to evaluate the ability of Pretrained Language Models (PLMs) to interpret negation. In this article, we build on Gubelmann and Handschuh (2022), which studies the modification of PLMs’ predictions as a function of the polarity of inputs, in English. Crucially, this test uses “self-contained” inputs ending with a masked position: depending on the polarity of a verb in the input, a particular token is either semantically ruled out or allowed at the masked position. By replicating Gubelmann and Handschuh (2022) experiments, we have uncovered flaws that weaken the conclusions that can be drawn from this test. We thus propose an improved version, the Self-Contained Neg Test, which is more controlled, more systematic, and entirely based on examples forming minimal pairs varying only in the presence or absence of verbal negation in English. When applying our test to the roberta and bert base and large models, we show that only roberta-large shows trends that match the expectations, while bert-base is mostly insensitive to negation. For all the tested models though, in a significant number of test instances the top-1 prediction remains the token that is semantically forbidden by the context, which shows how much room for improvement remains for a proper treatment of the negation phenomenon.

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.

L’analyseur biaffine de Dozat & Manning (2017), qui produit des arbres de dépendances syntaxiques, a été étendu avec succès aux graphes de dépendances syntaxico-sémantiques (Dozat & Manning, 2018). Ses performances sur les graphes sont étonnamment hautes étant donné que, sans la contrainte de devoir produire un arbre, les arcs pour une phrase donnée sont prédits indépendamment les uns des autres. Pour y remédier partiellement, tout en conservant la complexité O(n2 ) et l’architecture hautement parallélisable, nous proposons d’utiliser des tâches auxiliaires qui introduisent une forme d’interdépendance entre les arcs. Les expérimentations sur les trois jeux de données anglaises de la tâche 18 SemEval-2015 (Oepen et al., 2015), et sur des graphes syntaxiques profonds en français (Ribeyre et al., 2014) montrent une amélioration modeste mais systématique, par rapport à un système de base performant, utilisant un modèle de langue pré-entraîné. Notre méthode s’avère ainsi un moyen simple et robuste d’améliorer l’analyse vers graphes de dépendances.

The biaffine parser of (CITATION) was successfully extended to semantic dependency parsing (SDP) (CITATION). Its performance on graphs is surprisingly high given that, without the constraint of producing a tree, all arcs for a given sentence are predicted independently from each other (modulo a shared representation of tokens).To circumvent such an independence of decision, while retaining the O(n²) complexity and highly parallelizable architecture, we propose to use simple auxiliary tasks that introduce some form of interdependence between arcs. Experiments on the three English acyclic datasets of SemEval-2015 task 18 (CITATION), and on French deep syntactic cyclic graphs (CITATION) show modest but systematic performance gains on a near-state-of-the-art baseline using transformer-based contextualized representations. This provides a simple and robust method to boost SDP performance.

French, as many languages, lacks semantically annotated corpus data. Our aim is to provide the linguistic and NLP research communities with a gold standard sense-annotated corpus of French, using WordNet Unique Beginners as semantic tags, thus allowing for interoperability. In this paper, we report on the first phase of the project, which focused on the annotation of common nouns. The resulting dataset consists of more than 12,000 French noun occurrences which were annotated in double blind and adjudicated according to a carefully redefined set of supersenses. The resource is released online under a Creative Commons Licence.

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.

As opposed to word sense induction, word sense disambiguation (WSD) has the advantage of us-ing interpretable senses, but requires annotated data, which are quite rare for most languages except English (Miller et al. 1993; Fellbaum, 1998). In this paper, we investigate which strategy to adopt to achieve WSD for languages lacking data that was annotated specifically for the task, focusing on the particular case of verb disambiguation in French. We first study the usability of Eurosense (Bovi et al. 2017) , a multilingual corpus extracted from Europarl (Kohen, 2005) and automatically annotated with BabelNet (Navigli and Ponzetto, 2010) senses. Such a resource opened up the way to supervised and semi-supervised WSD for resourceless languages like French. While this perspective looked promising, our evaluation on French verbs was inconclusive and showed the annotated senses’ quality was not sufficient for supervised WSD on French verbs. Instead, we propose to use Wiktionary, a collaboratively edited, multilingual online dictionary, as a resource for WSD. Wiktionary provides both sense inventory and manually sense tagged examples which can be used to train supervised and semi-supervised WSD systems. Yet, because senses’ distribution differ in lexicographic examples found in Wiktionary with respect to natural text, we then focus on studying the impact on WSD of the training data size and senses’ distribution. Using state-of-the art semi-supervised systems, we report experiments of Wiktionary-based WSD for French verbs, evaluated on FrenchSemEval (FSE), a new dataset of French verbs manually annotated with wiktionary senses.

In this paper, we compare the use of linear versus neural classifiers in a greedy transition system for MWE identification. Both our linear and neural models achieve a new state-of-the-art on the PARSEME 1.1 shared task data sets, comprising 20 languages. Surprisingly, our best model is a simple feed-forward network with one hidden layer, although more sophisticated (recurrent) architectures were tested. The feedback from this study is that tuning a SVM is rather straightforward, whereas tuning our neural system revealed more challenging. Given the number of languages and the variety of linguistic phenomena to handle for the MWE identification task, we have designed an accurate tuning procedure, and we show that hyperparameters are better selected by using a majority-vote within random search configurations rather than a simple best configuration selection. Although the performance is rather good (better than both the best shared task system and the average of the best per-language results), further work is needed to improve the generalization power, especially on unseen MWEs.

This paper analyzes results on light-verb construction identification from the PARSEME shared-task, distinguishing between simple cases that could be directly learned from training data from more complex cases that require an extra level of semantic processing. We propose a simple baseline that beats the state of the art for the simple cases, and couple it with another simple baseline to handle the complex cases. We additionally present two other classifiers based on a richer set of features, with results surpassing the state of the art by 8 percentage points.

This paper presents Unsupervised Lexical Frame Induction, Task 2 of the International Workshop on Semantic Evaluation in 2019. Given a set of prespecified syntactic forms in context, the task requires that verbs and their arguments be clustered to resemble semantic frame structures. Results are useful in identifying polysemous words, i.e., those whose frame structures are not easily distinguished, as well as discerning semantic relations of the arguments. Evaluation of unsupervised frame induction methods fell into two tracks: Task A) Verb Clustering based on FrameNet 1.7; and B) Argument Clustering, with B.1) based on FrameNet’s core frame elements, and B.2) on VerbNet 3.2 semantic roles. The shared task attracted nine teams, of whom three reported promising results. This paper describes the task and its data, reports on methods and resources that these systems used, and offers a comparison to human annotation.

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.

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 describe the ATILF-LLF system built for the MWE 2017 Shared Task on automatic identification of verbal multiword expressions. We participated in the closed track only, for all the 18 available languages. Our system is a robust greedy transition-based system, in which MWE are identified through a MERGE transition. The system was meant to accommodate the variety of linguistic resources provided for each language, in terms of accompanying morphological and syntactic information. Using per-MWE Fscore, the system was ranked first for all but two languages (Hungarian and Romanian).

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%).

We present the French Question Bank, a treebank of 2600 questions. We show that classical parsing model performance drop while the inclusion of this data set is highly beneficial without harming the parsing of non-question data. when facing out-of- domain data with strong structural diver- gences. Two thirds being aligned with the QB (Judge et al., 2006) and being freely available, this treebank will prove useful to build robust NLP systems.

This paper reports on the development of a French FrameNet, within the ASFALDA project. While the first phase of the project focused on the development of a French set of frames and corresponding lexicon (Candito et al., 2014), this paper concentrates on the subsequent corpus annotation phase, which focused on four notional domains (commercial transactions, cognitive stances, causality and verbal communication). Given full coverage is not reachable for a relatively “new” FrameNet project, we advocate that focusing on specific notional domains allowed us to obtain full lexical coverage for the frames of these domains, while partially reflecting word sense ambiguities. Furthermore, as frames and roles were annotated on two French Treebanks (the French Treebank (Abeillé and Barrier, 2004) and the Sequoia Treebank (Candito and Seddah, 2012), we were able to extract a syntactico-semantic lexicon from the annotated frames. In the resource’s current status, there are 98 frames, 662 frame evoking words, 872 senses, and about 13000 annotated frames, with their semantic roles assigned to portions of text. The French FrameNet is freely available at alpage.inria.fr/asfalda.

We present here a general set of semantic frames to annotate causal expressions, with a rich lexicon in French and an annotated corpus of about 5000 instances of causal lexical items with their corresponding semantic frames. The aim of our project is to have both the largest possible coverage of causal phenomena in French, across all parts of speech, and have it linked to a general semantic framework such as FN, to benefit in particular from the relations between other semantic frames, e.g., temporal ones or intentional ones, and the underlying upper lexical ontology that enable some forms of reasoning. This is part of the larger ASFALDA French FrameNet project, which focuses on a few different notional domains which are interesting in their own right (Djemma et al., 2016), including cognitive positions and communication frames. In the process of building the French lexicon and preparing the annotation of the corpus, we had to remodel some of the frames proposed in FN based on English data, with hopefully more precise frame definitions to facilitate human annotation. This includes semantic clarifications of frames and frame elements, redundancy elimination, and added coverage. The result is arguably a significant improvement of the treatment of causality in FN itself.

Syntax plays an important role in the task of predicting the semantic structure of a sentence. But syntactic phenomena such as alternations, control and raising tend to obfuscate the relation between syntax and semantics. In this paper we predict the semantic structure of a sentence using a deeper syntax than what is usually done. This deep syntactic representation abstracts away from purely syntactic phenomena and proposes a structural organization of the sentence that is closer to the semantic representation. Experiments conducted on a French corpus annotated with semantic frames showed that a semantic parser reaches better performances with such a deep syntactic input.

We define a deep syntactic representation scheme for French, which abstracts away from surface syntactic variation and diathesis alternations, and describe the annotation of deep syntactic representations on top of the surface dependency trees of the Sequoia corpus. The resulting deep-annotated corpus, named deep-sequoia, is freely available, and hopefully useful for corpus linguistics studies and for training deep analyzers to prepare semantic analysis.

The Asfalda project aims to develop a French corpus with frame-based semantic annotations and automatic tools for shallow semantic analysis. We present the first part of the project: focusing on a set of notional domains, we delimited a subset of English frames, adapted them to French data when necessary, and developed the corresponding French lexicon. We believe that working domain by domain helped us to enforce the coherence of the resulting resource, and also has the advantage that, though the number of frames is limited (around a hundred), we obtain full coverage within a given domain.

In this paper, we introduce a set of resources that we have derived from the EST RÉPUBLICAIN CORPUS, a large, freely-available collection of regional newspaper articles in French, totaling 150 million words. Our resources are the result of a full NLP treatment of the EST RÉPUBLICAIN CORPUS: handling of multi-word expressions, lemmatization, part-of-speech tagging, and syntactic parsing. Processing of the corpus is carried out using statistical machine-learning approaches - joint model of data driven lemmatization and part- of-speech tagging, PCFG-LA and dependency based models for parsing - that have been shown to achieve state-of-the-art performance when evaluated on the French Treebank. Our derived resources are made freely available, and released according to the original Creative Common license for the EST RÉPUBLICAIN CORPUS. We additionally provide an overview of the use of these resources in various applications, in particular the use of generated word clusters from the corpus to alleviate lexical data sparseness for statistical parsing.

We first describe the automatic conversion of the French Treebank (Abeillé and Barrier, 2004), a constituency treebank, into typed projective dependency trees. In order to evaluate the overall quality of the resulting dependency treebank, and to quantify the cases where the projectivity constraint leads to wrong dependencies, we compare a subset of the converted treebank to manually validated dependency trees. We then compare the performance of two treebank-trained parsers that output typed dependency parses. The first parser is the MST parser (Mcdonald et al., 2006), which we directly train on dependency trees. The second parser is a combination of the Berkeley parser (Petrov et al., 2006) and a functional role labeler: trained on the original constituency treebank, the Berkeley parser first outputs constituency trees, which are then labeled with functional roles, and then converted into dependency trees. We found that used in combination with a high-accuracy French POS tagger, the MST parser performs a little better for unlabeled dependencies (UAS=90.3% versus 89.6%), and better for labeled dependencies (LAS=87.6% versus 85.6%).

Cet article présente une technique d’analyse syntaxique statistique à la fois en constituants et en dépendances. L’analyse procède en ajoutant des étiquettes fonctionnelles aux sorties d’un analyseur en constituants, entraîné sur le French Treebank, pour permettre l’extraction de dépendances typées. D’une part, nous spécifions d’un point de vue formel et linguistique les structures de dépendances à produire, ainsi que la procédure de conversion du corpus en constituants (le French Treebank) vers un corpus cible annoté en dépendances, et partiellement validé. D’autre part, nous décrivons l’approche algorithmique qui permet de réaliser automatiquement le typage des dépendances. En particulier, nous nous focalisons sur les méthodes d’apprentissage discriminantes d’étiquetage en fonctions grammaticales.

Cet article présente les résultats d’une évaluation exhaustive des principaux analyseurs syntaxiques probabilistes dit “lexicalisés” initialement conçus pour l’anglais, adaptés pour le français et évalués sur le CORPUS ARBORÉ DU FRANÇAIS (Abeillé et al., 2003) et le MODIFIED FRENCH TREEBANK (Schluter & van Genabith, 2007). Confirmant les résultats de (Crabbé & Candito, 2008), nous montrons que les modèles lexicalisés, à travers les modèles de Charniak (Charniak, 2000), ceux de Collins (Collins, 1999) et le modèle des TIG Stochastiques (Chiang, 2000), présentent des performances moindres face à un analyseur PCFG à Annotation Latente (Petrov et al., 2006). De plus, nous montrons que le choix d’un jeu d’annotations issus de tel ou tel treebank oriente fortement les résultats d’évaluations tant en constituance qu’en dépendance non typée. Comparés à (Schluter & van Genabith, 2008; Arun & Keller, 2005), tous nos résultats sont state-of-the-art et infirment l’hypothèse d’une difficulté particulière qu’aurait le français en terme d’analyse syntaxique probabiliste et de sources de données.

Nous montrons qu’il est possible d’obtenir une analyse syntaxique statistique satisfaisante pour le français sur du corpus journalistique, à partir des données issues du French Treebank du laboratoire LLF, à l’aide d’un algorithme d’analyse non lexicalisé.