Two Local Models for Neural Constituent Parsing

TL;DR

This paper explores two simple local neural models for constituent parsing, achieving highly competitive accuracy by making local decisions, demonstrating that local models can rival non-local feature-based parsers.

Contribution

Introduces and evaluates two straightforward local neural models for constituent parsing, showing their effectiveness in achieving state-of-the-art results.

Findings

Achieved 92.4% F1 on PTB

Achieved 87.3% F1 on CTB 5.1

Local models can rival non-local feature-based parsers

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.