Paper: Fast and Accurate Shift-Reduce Constituent Parsing

ACL ID P13-1043
Title Fast and Accurate Shift-Reduce Constituent Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2013
Authors

Shift-reduce dependency parsers give comparable accuracies to their chart- based counterparts, yet the best shift- reduce constituent parsers still lag behind the state-of-the-art. One important reason is the existence of unary nodes in phrase structure trees, which leads to different numbers of shift-reduce actions between different outputs for the same input. This turns out to have a large empirical impact on the framework of global training and beam search. We propose a simple yet effective extension to the shift-reduce process, which eliminates size differences between action sequences in beam-search. Our parser gives comparable accuracies to the state-of-the-art chart parsers. With linear run-time complexity, our parser is over an order of magnitude faster than the fastest chart parse...