Two Local Models for Neural Constituent Parsing
arXiv:1808.04850
Abstract
Non-local features have been exploited by syntactic parsers for capturing dependencies between sub output structures. Such features have been a key to the success of state-of-the-art statistical parsers. With the rise of deep learning, however, it has been shown that local output decisions can give highly competitive accuracies, thanks to the power of dense neural input representations that embody global syntactic information. We investigate two conceptually simple local neural models for constituent parsing, which make local decisions to constituent spans and CFG rules, respectively. Consistent with previous findings along the line, our best model gives highly competitive results, achieving the labeled bracketing F1 scores of 92.4% on PTB and 87.3% on CTB 5.1.
arXiv commentCOLING 2018
References in corpus (8)
- Sequence to Sequence Learning with Neural Networks
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- DyNet: The Dynamic Neural Network Toolkit
- Neural Probabilistic Model for Non-projective MST Parsing
- Bidirectional Tree-Structured LSTM with Head Lexicalization
- A Minimal Span-Based Neural Constituency Parser
- Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set
- Improving Neural Parsing by Disentangling Model Combination and Reranking Effects