Shift-Reduce Constituent Parsing with Neural Lookahead Features
Transition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which spans over non-local constituents. On the other hand, during incremental parsing, constituent informa...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , |
Format | Paper Journal Article |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
02.12.2016
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Transition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which spans over non-local constituents. On the other hand, during incremental parsing, constituent information on the right hand side of the current word is not utilized, which is a relative weakness of shift-reduce parsing. To address this limitation, we leverage a fast neural model to extract lookahead features. In particular, we build a bidirectional LSTM model, which leverages the full sentence information to predict the hierarchy of constituents that each word starts and ends. The results are then passed to a strong transition-based constituent parser as lookahead features. The resulting parser gives 1.3% absolute improvement in WSJ and 2.3% in CTB compared to the baseline, given the highest reported accuracies for fully-supervised parsing. |
---|---|
ISSN: | 2331-8422 |
DOI: | 10.48550/arxiv.1612.00567 |