Search Results for author: Philippe Muller

Found 35 papers, 4 papers with code

Weakly supervised discourse segmentation for multiparty oral conversations

1 code implementation EMNLP 2021 Lila Gravellier, Julie Hunter, Philippe Muller, Thomas Pellegrini, Isabelle Ferrané

Discourse segmentation, the first step of discourse analysis, has been shown to improve results for text summarization, translation and other NLP tasks.

Discourse Segmentation Segmentation +3

Multi-lingual Discourse Segmentation and Connective Identification: MELODI at Disrpt2021

no code implementations EMNLP (DISRPT) 2021 Morteza Kamaladdini Ezzabady, Philippe Muller, Chloé Braud

Building on the most successful architecture from the 2019 similar shared task, we leverage datasets in the same or similar languages to augment training data and improve on the best systems from the previous campaign on 3 out of 4 subtasks, with a mean improvement on all 16 datasets of 0. 85%.

Connective Detection Discourse Segmentation +2

The DISRPT 2021 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification

no code implementations EMNLP (DISRPT) 2021 Amir Zeldes, Yang Janet Liu, Mikel Iruskieta, Philippe Muller, Chloé Braud, Sonia Badene

In 2021, we organized the second iteration of a shared task dedicated to the underlying units used in discourse parsing across formalisms: the DISRPT Shared Task (Discourse Relation Parsing and Treebanking).

Connective Detection Relation +1

Plongements Interprétables pour la Détection de Biais Cachés (Interpretable Embeddings for Hidden Biases Detection)

no code implementations JEP/TALN/RECITAL 2021 Tom Bourgeade, Philippe Muller, Tim Van De Cruys

De nombreuses tâches sémantiques en TAL font usage de données collectées de manière semiautomatique, ce qui est souvent source d’artefacts indésirables qui peuvent affecter négativement les modèles entraînés sur celles-ci.

DiscSense: Automated Semantic Analysis of Discourse Markers

1 code implementation LREC 2020 Damien Sileo, Tim Van De Cruys, Camille Pradel, Philippe Muller

In this work, we take another perspective: using a model trained to predict discourse markers between sentence pairs, we predict plausible markers between sentence pairs with a known semantic relation (provided by existing classification datasets).

Classification General Classification +1

Which aspects of discourse relations are hard to learn? Primitive decomposition for discourse relation classification

no code implementations WS 2019 Charlotte Roze, Chlo{\'e} Braud, Philippe Muller

Discourse relation classification has proven to be a hard task, with rather low performance on several corpora that notably differ on the relation set they use.

General Classification Relation +1

A Pragmatics-Centered Evaluation Framework for Natural Language Understanding

2 code implementations LREC 2022 Damien Sileo, Tim Van-De-Cruys, Camille Pradel, Philippe Muller

New models for natural language understanding have recently made an unparalleled amount of progress, which has led some researchers to suggest that the models induce universal text representations.

Multi-Task Learning Natural Language Inference +1

Repr\'esentation s\'emantique distributionnelle et alignement de conversations par chat (Distributional semantic representation and alignment of online chat conversations )

no code implementations JEPTALNRECITAL 2019 Tom Bourgeade, Philippe Muller

Les mesures de similarit{\'e} textuelle ont une place importante en TAL, du fait de leurs nombreuses applications, en recherche d{'}information et en classification notamment.

Aprentissage non-supervis\'e pour l'appariement et l'\'etiquetage de cas cliniques en fran\ccais - DEFT2019 (Unsupervised learning for matching and labelling of french clincal cases - DEFT2019 )

no code implementations JEPTALNRECITAL 2019 Damien Sileo, Tim Van De Cruys, Philippe Muller, Camille Pradel

Nous pr{\'e}sentons le syst{\`e}me utilis{\'e} par l{'}{\'e}quipe Synapse/IRIT dans la comp{\'e}tition DEFT2019 portant sur deux t{\^a}ches li{\'e}es {\`a} des cas cliniques r{\'e}dig{\'e}s en fran{\c{c}}ais : l{'}une d{'}appariement entre des cas cliniques et des discussions, l{'}autre d{'}extraction de mots-clefs.

Analyse faiblement supervis\'ee de conversation en actes de dialogue (Weakly supervised dialog act analysis)

no code implementations JEPTALNRECITAL 2019 Catherine Thompson, Nicholas Asher, Philippe Muller, J{\'e}r{\'e}my Auguste

Nous nous int{\'e}ressons ici {\`a} l{'}analyse de conversation par chat dans un contexte orient{\'e}-t{\^a}che avec un conseiller technique s{'}adressant {\`a} un client, o{\`u} l{'}objectif est d{'}{\'e}tiqueter les {\'e}nonc{\'e}s en actes de dialogue, pour alimenter des analyses des conversations en aval.

Composition of Sentence Embeddings:Lessons from Statistical Relational Learning

no code implementations4 Apr 2019 Damien Sileo, Tim Van-De-Cruys, Camille Pradel, Philippe Muller

In this article, we show that previous work on relation prediction between texts implicitly uses compositions from baseline SRL models.

Natural Language Inference Relation +4

A Dependency Perspective on RST Discourse Parsing and Evaluation

no code implementations CL 2018 Mathieu Morey, Philippe Muller, Nicholas Asher

This allows us to characterize families of parsing strategies across the different frameworks, in particular with respect to the notion of headedness.

Constituency Parsing Dependency Parsing +1

Concat\'enation de r\'eseaux de neurones pour la classification de tweets, DEFT2018 (Concatenation of neural networks for tweets classification, DEFT2018 )

no code implementations JEPTALNRECITAL 2018 Damien Sileo, Tim Van De Cruys, Philippe Muller, Camille Pradel

Nous pr{\'e}sentons le syst{\`e}me utilis{\'e} par l{'}{\'e}quipe Melodi/Synapse D{\'e}veloppement dans la comp{\'e}tition DEFT2018 portant sur la classification de th{\'e}matique ou de sentiments de tweets en fran{\c{c}}ais.

Classification General Classification

Synapse at CAp 2017 NER challenge: Fasttext CRF

no code implementations14 Sep 2017 Damien Sileo, Camille Pradel, Philippe Muller, Tim Van De Cruys

We present our system for the CAp 2017 NER challenge which is about named entity recognition on French tweets.

named-entity-recognition Named Entity Recognition +2

Changement stylistique de phrases par apprentissage faiblement supervis\'e (Textual Style Transfer using Weakly Supervised Learning)

no code implementations JEPTALNRECITAL 2017 Damien Sileo, Camille Pradel, Philippe Muller, Tim Van De Cruys

Plusieurs t{\^a}ches en traitement du langage naturel impliquent de modifier des phrases en conservant au mieux leur sens, comme la reformulation, la compression, la simplification, chacune avec leurs propres donn{\'e}es et mod{\`e}les.

Style Transfer Weakly-supervised Learning

A General Framework for the Annotation of Causality Based on FrameNet

no code implementations LREC 2016 Laure Vieu, Philippe Muller, C, Marie ito, Marianne Djemaa

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.

Evaluating Temporal Graphs Built from Texts via Transitive Reduction

no code implementations16 Jan 2014 Xavier Tannier, Philippe Muller

Temporal information has been the focus of recent attention in information extraction, leading to some standardization effort, in particular for the task of relating events in a text.

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