Search Results for author:
Found 8 papers, 1 papers with code
Unifying Parsing and Tree-Structured Models for Generating Sentence Semantic Representations
As a result, the sentence embedding is computed according to an interpretable linguistic pattern and may be used on any downstream task.
BERTrade: Using Contextual Embeddings to Parse Old French
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.
Analyse en dépendances du français avec des plongements contextualisés (French dependency parsing with contextualized embeddings)
L’analyseur s’appuie sur de riches représentations lexicales issues notamment de BERT et de FASTTEXT.
Un modèle Transformer Génératif Pré-entrainé pour le _ _ _ _ _ _ français (Generative Pre-trained Transformer in _ _ _ _ _ _ (French) We introduce a French adaptation from the well-known GPT model)
Ces architectures sont en particulier pré-entraînées sur des tâches auto-supervisées et sont ainsi spécifiques pour une langue donnée.
How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks
This work addresses the question of the localization of syntactic information encoded in the transformers representations.
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data
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)
Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement
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.
Contrasting distinct structured views to learn sentence embeddings
We assume structure is crucial to build consistent representations as we expect sentence meaning to be a function from both syntax and semantic aspects.
