Shift-Reduce Constituent Parsing with Neural Lookahead Features
| Autor: | Jiangming Liu, Yue Zhang |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
Linguistics and Language Computer science Speech recognition 02 engineering and technology 010501 environmental sciences computer.software_genre Top-down parsing 01 natural sciences Parser combinator Artificial Intelligence 0202 electrical engineering electronic engineering information engineering Leverage (statistics) 0105 earth and related environmental sciences Computer Science - Computation and Language Parsing business.industry Communication Parsing expression grammar Computer Science Applications Human-Computer Interaction TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES 020201 artificial intelligence & image processing S-attributed grammar Artificial intelligence business Computation and Language (cs.CL) computer Natural language processing Sentence Bottom-up parsing |
| Zdroj: | Transactions of the Association for Computational Linguistics. 5:45-58 |
| ISSN: | 2307-387X |
| DOI: | 10.1162/tacl_a_00045 |
| Popis: | 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 consists of a sequence of 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 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, giving the highest reported accuracies for fully-supervised parsing. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|