Variable Beam Search for Generative Neural Parsing and Its Relevance for the Analysis of Neuro-Imaging Signal

TitreVariable Beam Search for Generative Neural Parsing and Its Relevance for the Analysis of Neuro-Imaging Signal
Publication TypeArticle dans des actes
Année de la conférence2019
AuthorsCrabbé, Benoît, Murielle Fabre, and Christophe Pallier
Nom de la conférenceProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Pagination1150–1160
PublisherAssociation for Computational Linguistics
Conference LocationHong Kong, China
Abstract

This paper describes a method of variable beam size inference for Recurrent Neural Network Grammar (rnng) by drawing inspiration from sequential Monte-Carlo methods such as particle filtering. The paper studies the relevance of such methods for speeding up the computations of direct generative parsing for rnng. But it also studies the potential cognitive interpretation of the underlying representations built by the search method (beam activity) through analysis of neuro-imaging signal.