Head-driven Phrase Structure Parsing in O($n^3$) Time Complexity

TL;DR

This paper introduces a novel $O(n^3)$ time complexity parser for Head-driven Phrase Structure Grammar (HPSG), combining constituent and dependency parsing benefits, and explores multilingual training from limited annotations.

Contribution

It proposes an improved head scorer enabling efficient HPSG parsing at $O(n^3)$, and investigates multilingual training from limited annotations, advancing HPSG parsing methods.

Findings

Achieved $O(n^3)$ time complexity in HPSG parsing.

Demonstrated effective multilingual training from limited annotations.

Provided insights into the strengths and general methods of HPSG-based parsing.

Abstract

Constituent and dependency parsing, the two classic forms of syntactic parsing, have been found to benefit from joint training and decoding under a uniform formalism, Head-driven Phrase Structure Grammar (HPSG). However, decoding this unified grammar has a higher time complexity ($O(n^5)$) than decoding either form individually ($O(n^3)$) since more factors have to be considered during decoding. We thus propose an improved head scorer that helps achieve a novel performance-preserved parser in $O$($n^3$) time complexity. Furthermore, on the basis of this proposed practical HPSG parser, we investigated the strengths of HPSG-based parsing and explored the general method of training an HPSG-based parser from only a constituent or dependency annotations in a multilingual scenario. We thus present a more effective, more in-depth, and general work on HPSG parsing.