Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, Epiciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Conference papers

Variable beam search for generative neural parsing and its relevance for the analysis of neuro-imaging signal

Benoît Crabbé 1 Murielle Fabre 1, 2, 3 Christophe Pallier 4 
1 LLF UMR7110 - Laboratoire de Linguistique Formelle
2 ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities
Inria de Paris
3 UPD7 - Université Paris Diderot - Paris 7
4 UNICOG-U992 - Neuroimagerie cognitive - Psychologie cognitive expérimentale
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.
Document type :
Conference papers
Complete list of metadata
https://hal.inria.fr/hal-02272303
Contributor : Murielle Fabre Connect in order to contact the contributor
Submitted on : Tuesday, August 27, 2019 - 4:17:04 PM
Last modification on : Wednesday, June 8, 2022 - 12:50:06 PM

Links full text

openaccess

Identifiers

Collections

CEA | UNIV-PARIS7 | CNRS | INRIA | LLF | INRIA2 | USPC | UNIV-PARIS-SACLAY | CEA-DRF | UNIV-PARIS | UP-SOCIETES-HUMANITES

Citation

Benoît Crabbé, Murielle Fabre, Christophe Pallier. Variable beam search for generative neural parsing and its relevance for the analysis of neuro-imaging signal. EMNLP-IJCNLP 2019 - Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Nov 2019, Hong-Kong, China. ⟨10.18653/v1/D19-1106⟩. ⟨hal-02272303⟩

Export

BibTeX TEI DC DCterms EndNote Datacite

Share

Metrics

Record views

179

 

Contact                    Legal Notice                    Personal Data