Search Results for author:
Found 22 papers, 11 papers with code
Contribution d’informations syntaxiques aux capacités de généralisation compositionelle des modèles seq2seq convolutifs (Assessing the Contribution of Syntactic Information for Compositional Generalization of seq2seq Convolutional Networks)
Le jeu de données SCAN, constitué d’un ensemble de commandes en langage naturel associées à des séquences d’action, a été spécifiquement conçu pour évaluer les capacités des réseaux de neurones à apprendre ce type de généralisation compositionnelle.
Fine-tuning pre-trained models for Automatic Speech Recognition, experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)
This is a report on results obtained in the development of speech recognition tools intended to support linguistic documentation efforts.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
What has LeBenchmark Learnt about French Syntax?
They are trained on very low level information (the raw speech signal), and do not have explicit lexical knowledge.
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing.
BERT is not The Count: Learning to Match Mathematical Statements with Proofs
While the first decoding method matches a proof to a statement without being aware of other statements or proofs, the second method treats the task as a global matching problem.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
Learning to Match Mathematical Statements with Proofs
The task is designed to improve the processing of research-level mathematical texts.
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.
Qu'apporte BERT \`a l'analyse syntaxique en constituants discontinus ? Une suite de tests pour \'evaluer les pr\'edictions de structures syntaxiques discontinues en anglais (What does BERT contribute to discontinuous constituency parsing ? A test suite to evaluate discontinuous constituency structure predictions in English)
Cet article propose d{'}analyser les apports d{'}un mod{\`e}le de langue pr{\'e}-entra{\^\i}n{\'e} de type BERT (bidirectional encoder representations from transformers) {\`a} l{'}analyse syntaxique en constituants discontinus en anglais (PTB, Penn Treebank).
Self-Supervised and Controlled Multi-Document Opinion Summarization
We address the problem of unsupervised abstractive summarization of collections of user generated reviews with self-supervision and control.
FlauBERT: Unsupervised Language Model Pre-training for French
Language models have become a key step to achieve state-of-the art results in many different Natural Language Processing (NLP) tasks.
Ranked #1 on
Natural Language Inference
on XNLI French
Unsupervised Aspect-Based Multi-Document Abstractive Summarization
User-generated reviews of products or services provide valuable information to customers.
Discontinuous Constituency Parsing with a Stack-Free Transition System and a Dynamic Oracle
We introduce a novel transition system for discontinuous constituency parsing.
Unlexicalized Transition-based Discontinuous Constituency Parsing
Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head (ii) bilexical statistics are crucial to solve ambiguities.
Privacy-preserving Neural Representations of Text
This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection.
Repr\'esentation et analyse automatique des discontinuit\'es syntaxiques dans les corpus arbor\'es en constituants du fran\ccais (Representation and parsing of syntactic discontinuities in French constituent treebanks)
Enfin, nos exp{\'e}riences montrent que la raret{\'e} des ph{\'e}nom{\`e}nes concern{\'e}s dans les donn{\'e}es fran{\c{c}}aises pose des difficult{\'e}s pour l{'}apprentissage et l{'}{\'e}valuation des structures discontinues.
Incremental Discontinuous Phrase Structure Parsing with the GAP Transition
This article introduces a novel transition system for discontinuous lexicalized constituent parsing called SR-GAP.
Multilingual Lexicalized Constituency Parsing with Word-Level Auxiliary Tasks
We introduce a constituency parser based on a bi-LSTM encoder adapted from recent work (Cross and Huang, 2016b; Kiperwasser and Goldberg, 2016), which can incorporate a lower level character biLSTM (Ballesteros et al., 2015; Plank et al., 2016).
Cross-lingual RST Discourse Parsing
Discourse parsing is an integral part of understanding information flow and argumentative structure in documents.
Ranked #10 on
Discourse Parsing
on RST-DT
Comparaison d'architectures neuronales pour l'analyse syntaxique en constituants
L{'}article traite de l{'}analyse syntaxique lexicalis{\'e}e pour les grammaires de constituants.
