UNIGE document Chapitre d'actes
previous document  unige:74747  next document
add to browser collection
Title

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

Authors
Published in Proceedings of the 19th Conference on Computational Language Learning. Beijing, China - July 30-31, 2015 - . 2015, p. 142-152
Abstract 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.
Full text
Structures
Research groups Laboratoire d'Analyse et de Traitement du Langage (LATL)
Geneva Artificial Intelligence Laboratory
Citation
(ISO format)
YAZDANI, Majid, HENDERSON, James. Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training. In: Proceedings of the 19th Conference on Computational Language Learning. Beijing, China. [s.l.] : [s.n.], 2015. p. 142-152. https://archive-ouverte.unige.ch/unige:74747

400 hits

187 downloads

Update

Deposited on : 2015-08-19

Export document
Format :
Citation style :