Search Results for author:
Found 35 papers, 4 papers with code
Mining Discourse Markers for Unsupervised Sentence Representation Learning
Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct.
Ranked #1 on
Relation Classification
on Discovery
A Pragmatics-Centered Evaluation Framework for Natural Language Understanding
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.
DiscSense: Automated Semantic Analysis of Discourse Markers
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).
Weakly supervised discourse segmentation for multiparty oral conversations
Discourse segmentation, the first step of discourse analysis, has been shown to improve results for text summarization, translation and other NLP tasks.
Synapse at CAp 2017 NER challenge: Fasttext CRF
We present our system for the CAp 2017 NER challenge which is about named entity recognition on French tweets.
Evaluating Temporal Graphs Built from Texts via Transitive Reduction
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.
A Dependency Perspective on RST Discourse Parsing and Evaluation
This allows us to characterize families of parsing strategies across the different frameworks, in particular with respect to the notion of headedness.
How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DT
This article evaluates purported progress over the past years in RST discourse parsing.
A Supervised Approach for Enriching the Relational Structure of Frame Semantics in FrameNet
Frame semantics is a theory of linguistic meanings, and is considered to be a useful framework for shallow semantic analysis of natural language.
Improving Composition of Sentence Embeddings through the Lens of Statistical Relational Learning
In this work, we show that textual relational models implicitly use compositions from baseline SRL models.
Developing a French FrameNet: Methodology and First results
The Asfalda project aims to develop a French corpus with frame-based semantic annotations and automatic tools for shallow semantic analysis.
An empirical resource for discovering cognitive principles of discourse organisation: the ANNODIS corpus
This paper describes the ANNODIS resource, a discourse-level annotated corpus for French.
Composition of Sentence Embeddings:Lessons from Statistical Relational Learning
In this article, we show that previous work on relation prediction between texts implicitly uses compositions from baseline SRL models.
Composition of Sentence Embeddings: Lessons from Statistical Relational Learning
In this article, we show that previous work on relation prediction between texts implicitly uses compositions from baseline SRL models.
ToNy: Contextual embeddings for accurate multilingual discourse segmentation of full documents
Segmentation is the first step in building practical discourse parsers, and is often neglected in discourse parsing studies.
Corpus Annotation within the French FrameNet: a Domain-by-domain Methodology
This paper reports on the development of a French FrameNet, within the ASFALDA project.
A General Framework for the Annotation of Causality Based on FrameNet
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.
Which aspects of discourse relations are hard to learn? Primitive decomposition for discourse relation classification
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.
Concat\'enation de r\'eseaux de neurones pour la classification de tweets, DEFT2018 (Concatenation of neural networks for tweets classification, DEFT2018 )
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.
Changement stylistique de phrases par apprentissage faiblement supervis\'e (Textual Style Transfer using Weakly Supervised Learning)
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.
Analyse faiblement supervis\'ee de conversation en actes de dialogue (Weakly supervised dialog act analysis)
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.
Repr\'esentation s\'emantique distributionnelle et alignement de conversations par chat (Distributional semantic representation and alignment of online chat conversations )
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 )
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.
The DISRPT 2021 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification
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).
Multi-lingual Discourse Segmentation and Connective Identification: MELODI at Disrpt2021
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%.
Plongements Interprétables pour la Détection de Biais Cachés (Interpretable Embeddings for Hidden Biases Detection)
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.
Predicting Political Orientation in News with Latent Discourse Structure to Improve Bias Understanding
With the growing number of information sources, the problem of media bias becomes worrying for a democratic society.
