Search Results for author:
Found 6 papers, 0 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.
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.
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.
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.
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.
