no code implementations • LREC 2022 • Loïc Grobol, Mathilde Regnault, Pedro Ortiz Suarez, Benoît Sagot, Laurent Romary, Benoit Crabbé
The successes of contextual word embeddings learned by training large-scale language models, while remarkable, have mostly occurred for languages where significant amounts of raw texts are available and where annotated data in downstream tasks have a relatively regular spelling.
no code implementations • JEP/TALN/RECITAL 2021 • Loïc Grobol, Benoit Crabbé
L’analyseur s’appuie sur de riches représentations lexicales issues notamment de BERT et de FASTTEXT.
no code implementations • JEP/TALN/RECITAL 2021 • Antoine Simoulin, Benoit Crabbé
Ces architectures sont en particulier pré-entraînées sur des tâches auto-supervisées et sont ainsi spécifiques pour une langue donnée.
no code implementations • ACL 2022 • Bingzhi Li, Guillaume Wisniewski, Benoit Crabbé
This work addresses the question of the localization of syntactic information encoded in the transformers representations.
no code implementations • NAACL (ACL) 2022 • Antoine Simoulin, Benoit Crabbé
As a result, the sentence embedding is computed according to an interpretable linguistic pattern and may be used on any downstream task.
1 code implementation • 23 Feb 2024 • Sergei Bogdanov, Alexandre Constantin, Timothée Bernard, Benoit Crabbé, Etienne Bernard
Large Language Models (LLMs) have shown impressive abilities in data annotation, opening the way for new approaches to solve classic NLP problems.
Ranked #1 on Few-shot NER on Few-NERD (INTRA)
no code implementations • EMNLP 2021 • Bingzhi Li, Guillaume Wisniewski, Benoit Crabbé
Many recent works have demonstrated that unsupervised sentence representations of neural networks encode syntactic information by observing that neural language models are able to predict the agreement between a verb and its subject.
no code implementations • EACL 2021 • Antoine Simoulin, Benoit Crabbé
We assume structure is crucial to build consistent representations as we expect sentence meaning to be a function from both syntax and semantic aspects.