Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training

Conférence Chapitre d'actes Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training eng 2015 author Yazdani Majid 813004 author Henderson James 529988 142-152 10.18653/v1/k15-1015 We propose a discriminatively trained recurrent neural network (RNN) that predicts the actions for a fast and accurate shift-reduce dependency parser. The RNN uses its output-dependent model structure to compute hidden vectors that encode the preceding partial parse, and uses them to estimate probabilities of parser actions. Unlike a similar previous generative model (Henderson and Titov, 2010), the RNN is trained discriminatively to optimize a fast beam search. This beam search prunes after each shift action, so we add a correctness probability to each shift action and train this score to discriminate between correct and incorrect sequences of parser actions. We also speed up parsing time by caching computations for frequent feature combinations, including during training, giving us both faster training and a form of backoff smoothing. The resulting parser is over 35 times faster than its generative counterpart with nearly the same accuracy, producing state-of-art dependency parsing results while requiring minimal feature engineering. Dewey 025.063 Dewey 410 13 Centre universitaire d'informatique 0D3 32 Département d'informatique 18 82 Département de linguistique 39 false 730 Geneva Artificial Intelligence Laboratory 722 Laboratoire d'Analyse et de Traitement du Langage (LATL) Proceedings of the 19th Conference on Computational Language Learning July 30-31, 2015 Beijing, China ba9fb8be-23d5-48a3-a301-0930e22599d0 Proceedings chapter (Published version) Public 109_Paper.pdf 318626 application/pdf openAccess Centres et instituts / Centre universitaire d'informatique Faculté des sciences / Département d'informatique Faculté des lettres / Département de linguistique

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training	Proceedings of the 19th Conference on Computational Language Learning			2015	786	612

Archive ouverte UNIGE

Yazdani, Majid