Search Results for author: Olivier Ferret

Found 62 papers, 9 papers with code

Mieux utiliser BERT pour la détection d’évènements à partir de peu d’exemples (Better exploitation of BERT for few-shot event detection)

no code implementations JEP/TALN/RECITAL 2022 Aboubacar Tuo, Romaric Besançon, Olivier Ferret, Julien Tourille

Les méthodes actuelles pour la détection d’évènements, qui s’appuient essentiellement sur l’apprentissage supervisé profond, s’avèrent très coûteuses en données annotées.

Event Detection

Décontextualiser des plongements contextuels pour construire des thésaurus distributionnels (Decontextualizing contextual embeddings for building distributional thesauri )

no code implementations JEP/TALN/RECITAL 2022 Olivier Ferret

Même si les modèles de langue contextuels sont aujourd’hui dominants en traitement automatique des langues, les représentations qu’ils construisent ne sont pas toujours adaptées à toutes les utilisations.

Stratégies d’adaptation pour la reconnaissance d’entités médicales en français (Adaptation strategies for biomedical named entity recognition in French)

no code implementations JEP/TALN/RECITAL 2022 Tiphaine Le Clercq de Lannoy, Romaric Besançon, Olivier Ferret, Julien Tourille, Frédérique Brin-Henry, Bianca Vieru

Dans un contexte où peu de corpus annotés pour l’extraction d’entités médicales sont disponibles, nous étudions dans cet article une approche hybride combinant utilisation de connaissances spécialisées et adaptation de modèles de langues en mettant l’accent sur l’effet du pré-entraînement d’un modèle de langue généraliste (CamemBERT) sur différents corpus.

named-entity-recognition Named Entity Recognition +1

Can We Guide a Multi-Hop Reasoning Language Model to Incrementally Learn at Each Single-Hop?

1 code implementation COLING 2022 Jesus Lovon-Melgarejo, Jose G. Moreno, Romaric Besançon, Olivier Ferret, Lynda Tamine

Despite the success of state-of-the-art pre-trained language models (PLMs) on a series of multi-hop reasoning tasks, they still suffer from their limited abilities to transfer learning from simple to complex tasks and vice-versa.

Language Modelling Multiple-choice +3

CLISTER : A Corpus for Semantic Textual Similarity in French Clinical Narratives

no code implementations LREC 2022 Nicolas Hiebel, Olivier Ferret, Karën Fort, Aurélie Névéol

We introduce a definition of similarity that is guided by clinical facts and apply it to the development of a new French corpus of 1, 000 sentence pairs manually annotated according to similarity scores.

Semantic Similarity Semantic Textual Similarity +5

Re-train or Train from Scratch? Comparing Pre-training Strategies of BERT in the Medical Domain

no code implementations LREC 2022 Hicham El Boukkouri, Olivier Ferret, Thomas Lavergne, Pierre Zweigenbaum

BERT models used in specialized domains all seem to be the result of a simple strategy: initializing with the original BERT and then resuming pre-training on a specialized corpus.

Exploration des relations sémantiques sous-jacentes aux plongements contextuels de mots (Exploring semantic relations underlying contextual word embeddings)

no code implementations JEP/TALN/RECITAL 2021 Olivier Ferret

De nombreuses études ont récemment été réalisées pour étudier les propriétés des modèles de langue contextuels mais, de manière surprenante, seules quelques-unes d’entre elles se concentrent sur les propriétés de ces modèles en termes de similarité sémantique.

Word Embeddings

Cross-modal Retrieval for Knowledge-based Visual Question Answering

1 code implementation11 Jan 2024 Paul Lerner, Olivier Ferret, Camille Guinaudeau

Knowledge-based Visual Question Answering about Named Entities is a challenging task that requires retrieving information from a multimodal Knowledge Base.

Cross-Modal Retrieval Question Answering +2

Probing Pretrained Language Models with Hierarchy Properties

no code implementations15 Dec 2023 Jesús Lovón-Melgarejo, Jose G. Moreno, Romaric Besançon, Olivier Ferret, Lynda Tamine

In this work, we propose a task-agnostic evaluation method able to evaluate to what extent PLMs can capture complex taxonomy relations, such as ancestors and siblings.

Hypernym Discovery Information Retrieval +2

TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation

1 code implementation11 Jul 2023 Paul Grimal, Hervé Le Borgne, Olivier Ferret, Julien Tourille

While several metrics have been proposed to assess the rendering of images, it is crucial for Text-to-Image (T2I) models, which generate images based on a prompt, to consider additional aspects such as to which extent the generated image matches the important content of the prompt.

Text-to-Image Generation

Multimodal Inverse Cloze Task for Knowledge-based Visual Question Answering

1 code implementation11 Jan 2023 Paul Lerner, Olivier Ferret, Camille Guinaudeau

We present a new pre-training method, Multimodal Inverse Cloze Task, for Knowledge-based Visual Question Answering about named Entities (KVQAE).

Question Answering Reading Comprehension +3

Using Distributional Principles for the Semantic Study of Contextual Language Models

no code implementations23 Nov 2021 Olivier Ferret

Many studies were recently done for investigating the properties of contextual language models but surprisingly, only a few of them consider the properties of these models in terms of semantic similarity.

Semantic Similarity Semantic Textual Similarity

Multimodal Entity Linking for Tweets

2 code implementations7 Apr 2021 Omar Adjali, Romaric Besançon, Olivier Ferret, Herve Le Borgne, Brigitte Grau

In many information extraction applications, entity linking (EL) has emerged as a crucial task that allows leveraging information about named entities from a knowledge base.

Entity Linking

CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters

2 code implementations COLING 2020 Hicham El Boukkouri, Olivier Ferret, Thomas Lavergne, Hiroshi Noji, Pierre Zweigenbaum, Junichi Tsujii

Due to the compelling improvements brought by BERT, many recent representation models adopted the Transformer architecture as their main building block, consequently inheriting the wordpiece tokenization system despite it not being intrinsically linked to the notion of Transformers.

Clinical Concept Extraction Drug–drug Interaction Extraction +3

Repr\'esentation dynamique et sp\'ecifique du contexte textuel pour l'extraction d'\'ev\'enements (Dynamic and specific textual context representation for event extraction)

no code implementations JEPTALNRECITAL 2020 Dorian Kodelja, Romaric Besan{\c{c}}on, Olivier Ferret

Dans cet article, focalis{\'e} sur l{'}extraction supervis{\'e}e de mentions d{'}{\'e}v{\'e}nements dans les textes, nous proposons d{'}{\'e}tendre un mod{\`e}le op{\'e}rant au niveau phrastique et reposant sur une architecture neuronale de convolution de graphe exploitant les d{\'e}pendances syntaxiques.

Event Extraction

Building a Multimodal Entity Linking Dataset From Tweets

no code implementations LREC 2020 Omar Adjali, Romaric Besan{\c{c}}on, Olivier Ferret, Herv{\'e} Le Borgne, Brigitte Grau

The method collects text and images to jointly build a corpus of tweets with ambiguous mentions along with a Twitter KB defining the entities.

Entity Linking Event Detection +1

Extrinsic Evaluation of French Dependency Parsers on a Specialized Corpus: Comparison of Distributional Thesauri

no code implementations LREC 2020 Ludovic Tanguy, Pauline Brunet, Olivier Ferret

We present a study in which we compare 11 different French dependency parsers on a specialized corpus (consisting of research articles on NLP from the proceedings of the TALN conference).

Which Dependency Parser to Use for Distributional Semantics in a Specialized Domain?

no code implementations LREC 2020 Pauline Brunet, Olivier Ferret, Ludovic Tanguy

We present a study whose objective is to compare several dependency parsers for English applied to a specialized corpus for building distributional count-based models from syntactic dependencies.

Searching News Articles Using an Event Knowledge Graph Leveraged by Wikidata

no code implementations11 Apr 2019 Charlotte Rudnik, Thibault Ehrhart, Olivier Ferret, Denis Teyssou, Raphaël Troncy, Xavier Tannier

News agencies produce thousands of multimedia stories describing events happening in the world that are either scheduled such as sports competitions, political summits and elections, or breaking events such as military conflicts, terrorist attacks, natural disasters, etc.

Using pseudo-senses for improving the extraction of synonyms from word embeddings

no code implementations ACL 2018 Olivier Ferret

The methods proposed recently for specializing word embeddings according to a particular perspective generally rely on external knowledge.

Dimensionality Reduction Semantic Similarity +3

Des pseudo-sens pour am\'eliorer l'extraction de synonymes \`a partir de plongements lexicaux (Pseudo-senses for improving the extraction of synonyms from word embeddings)

no code implementations JEPTALNRECITAL 2018 Olivier Ferret

Au-del{\`a} des mod{\`e}les destin{\'e}s {\`a} construire des plongements lexicaux {\`a} partir de corpus, des m{\'e}thodes de sp{\'e}cialisation de ces repr{\'e}sentations selon diff{\'e}rentes orientations ont {\'e}t{\'e} propos{\'e}es.

Word Embeddings

Taking into account Inter-sentence Similarity for Update Summarization

no code implementations IJCNLP 2017 Ma{\^a}li Mnasri, Ga{\"e}l de Chalendar, Olivier Ferret

Following Gillick and Favre (2009), a lot of work about extractive summarization has modeled this task by associating two contrary constraints: one aims at maximizing the coverage of the summary with respect to its information content while the other represents its size limit.

Document Summarization Extractive Summarization +5

Turning Distributional Thesauri into Word Vectors for Synonym Extraction and Expansion

no code implementations IJCNLP 2017 Olivier Ferret

In this article, we propose to investigate a new problem consisting in turning a distributional thesaurus into dense word vectors.

Graph Embedding Semantic Textual Similarity +1

Unsupervised Event Clustering and Aggregation from Newswire and Web Articles

no code implementations WS 2017 Swen Ribeiro, Olivier Ferret, Xavier Tannier

In this paper, we present an unsupervised pipeline approach for clustering news articles based on identified event instances in their content.

Clustering Document Summarization +1

Construire des repr\'esentations denses \`a partir de th\'esaurus distributionnels (Distributional Thesaurus Embedding and its Applications)

no code implementations JEPTALNRECITAL 2017 Olivier Ferret

Dans cet article, nous nous int{\'e}ressons {\`a} un nouveau probl{\`e}me, appel{\'e} plongement de th{\'e}saurus, consistant {\`a} transformer un th{\'e}saurus distributionnel en une repr{\'e}sentation dense de mots.

Int\'egration de la similarit\'e entre phrases comme crit\`ere pour le r\'esum\'e multi-document (Integrating sentence similarity as a constraint for multi-document summarization)

no code implementations JEPTALNRECITAL 2016 Ma{\^a}li Mnasri, Ga{\"e}l de Chalendar, Olivier Ferret

Dans cet article, nous reprenons le cadre d{\'e}fini par Gillick {\&} Favre (2009) mais nous examinons comment et dans quelle mesure la prise en compte explicite de la similarit{\'e} s{\'e}mantique des phrases peut am{\'e}liorer les performances d{'}un syst{\`e}me de r{\'e}sum{\'e} multi-document.

Document Summarization Multi-Document Summarization +2

A Dataset for Open Event Extraction in English

no code implementations LREC 2016 Kiem-Hieu Nguyen, Xavier Tannier, Olivier Ferret, Romaric Besan{\c{c}}on

We detail the methodology used for building the corpus and evaluate some existing systems on this new data.

Event Extraction

D\'esambigu\"\isation d'entit\'es pour l'induction non supervis\'ee de sch\'emas \'ev\'enementiels

no code implementations JEPTALNRECITAL 2015 Kiem-Hieu Nguyen, Xavier Tannier, Olivier Ferret, Romaric Besan{\c{c}}on

Les pr{\'e}c{\'e}dentes m{\'e}thodes de la litt{\'e}rature utilisent uniquement les t{\^e}tes des syntagmes pour repr{\'e}senter les entit{\'e}s. Pourtant, le groupe complet (par exemple, {''}un homme arm{\'e}{''}) apporte une information plus discriminante (que {''}homme{''}).

SENTER

D\'eclasser les voisins non s\'emantiques pour am\'eliorer les th\'esaurus distributionnels

no code implementations JEPTALNRECITAL 2015 Olivier Ferret

La plupart des m{\'e}thodes d{'}am{\'e}lioration des th{\'e}saurus distributionnels se focalisent sur les moyens {--} repr{\'e}sentations ou mesures de similarit{\'e} {--} de mieux d{\'e}tecter la similarit{\'e} s{\'e}mantique entre les mots.

Evaluation of different strategies for domain adaptation in opinion mining

no code implementations LREC 2014 Garcia-Fern, Anne ez, Olivier Ferret, Marco Dinarelli

The work presented in this article takes place in the field of opinion mining and aims more particularly at finding the polarity of a text by relying on machine learning methods.

Domain Adaptation Opinion Mining +2

Evaluation of Unsupervised Information Extraction

no code implementations LREC 2012 Wei Wang, Romaric Besan{\c{c}}on, Olivier Ferret, Brigitte Grau

Unsupervised methods gain more and more attention nowadays in information extraction area, which allows to design more open extraction systems.

Clustering Open Information Extraction +2

Evaluation of a Complex Information Extraction Application in Specific Domain

no code implementations LREC 2012 Romaric Besan{\c{c}}on, Olivier Ferret, Ludovic Jean-Louis

Operational intelligence applications in specific domains are developed using numerous natural language processing technologies and tools.

Clustering Named Entity Recognition (NER)

Cannot find the paper you are looking for? You can Submit a new open access paper.