Comparaison d’architectures neuronales pour l’analyse syntaxique en constituants

Maximin Coavoux, Benoit Crabbé

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The article deals with lexicalized constituent parsing in a transition-based framework. Typical statistical approaches for this task are based on an unstructured representation of the lexicon. Words are represented by discrete unrelated symbols.
Instead, our proposal relies on dense vector representations (embeddings) that are able to encode similarity between symbols: words, part-of-speech tags and phrase structure symbols. The article studies and compares 3 increasingly complex
neural network architectures, which are fed symbol embeddings. The experiments suggest that the information given by embeddings is best captured by a deep architecture with a non-linear layer.
Original languageFrench
Title of host publication22nd Conference on Automatic Processing of Natural Languages (CAEN 2015)
Pages293–304
Number of pages12
Publication statusPublished - 2015
Event22nd Conference on Automatic Processing of Natural Languages - Caen, France
Duration: 22 Jun 201525 Jun 2015
https://taln2015.greyc.fr/

Conference

Conference22nd Conference on Automatic Processing of Natural Languages
Abbreviated titleCAEN 2015
Country/TerritoryFrance
CityCaen
Period22/06/1525/06/15
Internet address

Cite this