Search Results for author:
Found 92 papers, 6 papers with code
Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions
In this paper, we propose \textbf{N3} (\textbf{N}eural \textbf{N}etworks from \textbf{N}atural Language) - a new paradigm of synthesizing task-specific neural networks from language descriptions and a generic pre-trained model.
FlauBERT : des mod\`eles de langue contextualis\'es pr\'e-entra\^\in\'es pour le fran\ccais (FlauBERT : Unsupervised Language Model Pre-training for French)
Les mod{\`e}les de langue pr{\'e}-entra{\^\i}n{\'e}s sont d{\'e}sormais indispensables pour obtenir des r{\'e}sultats {\`a} l{'}{\'e}tat-de-l{'}art dans de nombreuses t{\^a}ches du TALN.
Symbolisme phon\'etique du genre dans les pr\'enoms fran\ccais (Sex-biased sound symbolism in French first names)
Le symbolisme phon{\'e}tique sugg{\`e}re un lien naturel entre les sons et la signification d{'}un mot.
\'Etude des variations s\'emantiques \`a travers plusieurs dimensions (Studying semantic variations through several dimensions )
Nous exp{\'e}rimentons sur un corpus de rapports financiers d{'}entreprises fran{\c{c}}aises, pour appr{\'e}hender les enjeux et pr{\'e}occupations propres {\`a} certaines p{\'e}riodes, acteurs et secteurs d{'}activit{\'e}s.
Frame-Based Annotation of Multimodal Corpora: Tracking (A)Synchronies in Meaning Construction
Multimodal aspects of human communication are key in several applications of Natural Language Processing, such as Machine Translation and Natural Language Generation.
English WordNet 2020: Improving and Extending a WordNet for English using an Open-Source Methodology
WordNet, while one of the most widely used resources for NLP, has not been updated for a long time, and as such a new project English WordNet has arisen to continue the development of the model under an open-source paradigm.
ELRI: A Decentralised Network of National Relay Stations to Collect, Prepare and Share Language Resources
We describe the European Language Resource Infrastructure (ELRI), a decentralised network to help collect, prepare and share language resources.
Ontology Matching Using Convolutional Neural Networks
In order to achieve interoperability of information in the context of the Semantic Web, it is necessary to find effective ways to align different ontologies.
Inclusion of Lithological terms (rocks and minerals) in The Open Wordnet for English
We extend the Open WordNet for English (OWN-EN) with rock-related and other lithological terms using the authoritative source of GBA{'}s Thesaurus.
Apprentissage de plongements de mots dynamiques avec r\'egularisation de la d\'erive (Learning dynamic word embeddings with drift regularisation)
L{'}usage, le sens et la connotation des mots peuvent changer au cours du temps.
Towards Incremental Learning of Word Embeddings Using Context Informativeness
In this paper, we investigate the task of learning word embeddings from very sparse data in an incremental, cognitively-plausible way.
Inducing Document Structure for Aspect-based Summarization
In addition to improvements in summarization over topic-agnostic baselines, we demonstrate the benefit of the learnt document structure: we show that our models (a) learn to accurately segment documents by aspect; (b) can leverage the structure to produce both abstractive and extractive aspect-based summaries; and (c) that structure is particularly advantageous for summarizing long documents.
Interpr\'etation et visualisation contextuelle de NOTAMs (messages aux navigants a\'eriens) ()
Dans cet article, nous pr{\'e}sentons une d{\'e}monstration de visualisation de l{'}information extraite automatiquement de la partie textuelle des NOTAMs.
Bayesian Inference Semantics: A Modelling System and A Test Suite
We present BIS, a Bayesian Inference Semantics, for probabilistic reasoning in natural language.
Learning with Noise-Contrastive Estimation: Easing training by learning to scale
Noise-Contrastive Estimation (NCE) is a learning criterion that is regularly used to train neural language models in place of Maximum Likelihood Estimation, since it avoids the computational bottleneck caused by the output softmax.
Butterfly Effects in Frame Semantic Parsing: impact of data processing on model ranking
Knowing the state-of-the-art for a particular task is an essential component of any computational linguistics investigation.
LSE au DEFT 2018 : Classification de tweets bas\'ee sur les r\'eseaux de neurones profonds (LSE at DEFT 2018 : Sentiment analysis model based on deep learning)
Dans ce papier, nous d{\'e}crivons les syst{\`e}mes d{\'e}velopp{\'e}s au LSE pour le DEFT 2018 sur les t{\^a}ches 1 et 2 qui consistent {\`a} classifier des tweets.
A comparative study of word embeddings and other features for lexical complexity detection in French
Lexical complexity detection is an important step for automatic text simplification which serves to make informed lexical substitutions.
Algorithmes \`a base d'\'echantillonage pour l'entra\^\inement de mod\`eles de langue neuronaux (Here the title in English)
L{'}estimation contrastive bruit{\'e}e (NCE) et l{'}{\'e}chantillonage par importance (IS) sont des proc{\'e}dures d{'}entra{\^\i}nement bas{\'e}es sur l{'}{\'e}chantillonage, que l{'}on utilise habituellement {\`a} la place de l{'}estimation du maximum de vraisemblance (MLE) pour {\'e}viter le calcul du softmax lorsque l{'}on entra{\^\i}ne des mod{\`e}les de langue neuronaux.
Accurate Supervised and Semi-Supervised Machine Reading for Long Documents
We also evaluate the model in a semi-supervised setting by downsampling the WikiReading training set to create increasingly smaller amounts of supervision, while leaving the full unlabeled document corpus to train a sequence autoencoder on document windows.
Topic Signatures in Political Campaign Speeches
Highlighting the recurrence of topics usage in candidates speeches is a key feature to identify the main ideas of each candidate during a political campaign.
Character and Subword-Based Word Representation for Neural Language Modeling Prediction
Most of neural language models use different kinds of embeddings for word prediction.
Coarse-to-Fine Question Answering for Long Documents
We present a framework for question answering that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models.
Repr\'esentations continues d\'eriv\'ees des caract\`eres pour un mod\`ele de langue neuronal \`a vocabulaire ouvert (Opening the vocabulary of neural language models with character-level word representations)
Les repr{\'e}sentations continues des mots sont calcul{\'e}es {\`a} la vol{\'e}e {\`a} partir des caract{\`e}res les composant, gr{\`a}ce {\`a} une couche convolutionnelle suivie d{'}une couche de regroupement (pooling).
Adaptation au domaine pour l'analyse morpho-syntaxique (Domain Adaptation for PoS tagging)
Ce travail cherche {\`a} comprendre pourquoi les performances d{'}un analyseur morpho-syntaxiques chutent fortement lorsque celui-ci est utilis{\'e} sur des donn{\'e}es hors domaine.
An experimental analysis of Noise-Contrastive Estimation: the noise distribution matters
Noise Contrastive Estimation (NCE) is a learning procedure that is regularly used to train neural language models, since it avoids the computational bottleneck caused by the output softmax.
Valencer: an API to Query Valence Patterns in FrameNet
This paper introduces Valencer: a RESTful API to search for annotated sentences matching a given combination of syntactic realizations of the arguments of a predicate {--} also called {`}valence pattern{'} {--} in the FrameNet database.
Une m\'ethode non-supervis\'ee pour la segmentation morphologique et l'apprentissage de morphotactique \`a l'aide de processus de Pitman-Yor (An unsupervised method for joint morphological segmentation and morphotactics learning using Pitman-Yor processes)
Cet article pr{\'e}sente un mod{\`e}le bay{\'e}sien non-param{\'e}trique pour la segmentation morphologique non supervis{\'e}e. Ce mod{\`e}le semi-markovien s{'}appuie sur des classes latentes de morph{\`e}mes afin de mod{\'e}liser les caract{\'e}ristiques morphotactiques du lexique, et son caract{\`e}re non-param{\'e}trique lui permet de s{'}adapter aux donn{\'e}es sans avoir {\`a} sp{\'e}cifier {\`a} l{'}avance l{'}inventaire des morph{\`e}mes ainsi que leurs classes.
Optimiser l'adaptation en ligne d'un module de compr\'ehension de la parole avec un algorithme de bandit contre un adversaire (Adversarial bandit for optimising online active learning of spoken language understanding)
De nombreux modules de compr{\'e}hension de la parole ont en commun d{'}{\^e}tre probabilistes et bas{\'e}s sur des algorithmes d{'}apprentissage automatique.
Perception audio-visuelle de s\'equences VCV produites par des personnes porteuses de Trisomie 21 : une \'etude pr\'eliminaire (Auditory-visual Perception of VCVs Produced by People with Down Syndrome: a Preliminary Study)
Pour les deux locuteurs impliqu{\'e}s, l{'}intelligibilit{\'e} visuelle est n{\'e}anmoins {\'e}quivalente {\`a} celle des deux locuteurs ordinaires et compensent le d{\'e}ficit d{'}intelligibilit{\'e} auditive.
Suivi de contours d'articulateurs orofaciaux \`a partir d'IRM dynamique (Orofacial articulators tracking from dynamic MRI)
Nous pr{\'e}sentons une m{\'e}thode de pr{\'e}diction de contours m{\'e}diosagittaux des organes orofaciaux de la parole et la d{\'e}glutition {\`a} partir d{'}images IRM dynamiques.
MultiVec: a Multilingual and Multilevel Representation Learning Toolkit for NLP
We present MultiVec, a new toolkit for computing continuous representations for text at different granularity levels (word-level or sequences of words).
Semantic Links for Portuguese
This paper describes work on incorporating Princenton{'}s WordNet morphosemantics links to the fabric of the Portuguese OpenWordNet-PT.
Grammaires phrastiques et discursives fond\'ees sur les TAG : une approche de D-STAG avec les ACG
Cet encodage permet d{'}une part d{'}utiliser l{'}ordre sup{\'e}rieur pour l{'}interpr{\'e}tation s{\'e}mantique afin de construire des structures qui soient des DAG et non des arbres, et d{'}autre part d{'}utiliser les propri{\'e}t{\'e}s de composition d{'}ACG pour r{\'e}aliser naturellement l{'}interface entre grammaire phrastique et grammaire discursive.
Apprentissage discriminant des mod\`eles continus de traduction
Alors que les r{\'e}seaux neuronaux occupent une place de plus en plus importante dans le traitement automatique des langues, les m{\'e}thodes d{'}apprentissage actuelles utilisent pour la plupart des crit{\`e}res qui sont d{\'e}corr{\'e}l{\'e}s de l{'}application.
Oublier ce qu'on sait, pour mieux apprendre ce qu'on ne sait pas : une \'etude sur les contraintes de type dans les mod\`eles CRF
Quand on dispose de connaissances a priori sur les sorties possibles d{'}un probl{\`e}me d{'}{\'e}tiquetage, il semble souhaitable d{'}inclure cette information lors de l{'}apprentissage pour simplifier la t{\^a}che de mod{\'e}lisation et acc{\'e}l{\'e}rer les traitements.
NomLex-PT: A Lexicon of Portuguese Nominalizations
This paper presents NomLex-PT, a lexical resource describing Portuguese nominalizations.
Representation of linguistic and domain knowledge for second language learning in virtual worlds
There has been much debate, both theoretical and practical, on how to link ontologies and lexicons in natural language processing (NLP) applications.
