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

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.
Complete list of metadata

https://hal.inria.fr/hal-02272303
Contributor : Murielle Fabre <>
Submitted on : Tuesday, August 27, 2019 - 4:17:04 PM
Last modification on : Tuesday, September 1, 2020 - 2:22:23 PM

Links full text

Identifiers

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⟩

Share

Metrics

Record views

285