In-Order Transition-based Constituent Parsing

TL;DR

This paper introduces an in-order traversal-based transition system for neural constituent parsing, combining advantages of bottom-up and top-down strategies to improve accuracy on the WSJ benchmark.

Contribution

The paper proposes a novel in-order traversal transition system that balances bottom-up and top-down information for improved constituent parsing performance.

Findings

Achieves 91.8 F1 on WSJ benchmark

Improves to 93.6 F1 with supervised reranking

Reaches 94.2 F1 with semi-supervised reranking

Abstract

Both bottom-up and top-down strategies have been used for neural transition-based constituent parsing. The parsing strategies differ in terms of the order in which they recognize productions in the derivation tree, where bottom-up strategies and top-down strategies take post-order and pre-order traversal over trees, respectively. Bottom-up parsers benefit from rich features from readily built partial parses, but lack lookahead guidance in the parsing process; top-down parsers benefit from non-local guidance for local decisions, but rely on a strong encoder over the input to predict a constituent hierarchy before its construction.To mitigate both issues, we propose a novel parsing system based on in-order traversal over syntactic trees, designing a set of transition actions to find a compromise between bottom-up constituent information and top-down lookahead information. Based on stack-LSTM, our psycholinguistically motivated constituent parsing system achieves 91.8 F1 on WSJ benchmark. Furthermore, the system achieves 93.6 F1 with supervised reranking and 94.2 F1 with semi-supervised reranking, which are the best results on the WSJ benchmark.