Head-Driven Phrase Structure Grammar Parsing on Penn Treebank

ACL 2019  ·  Junru Zhou, Hai Zhao ·

Head-driven phrase structure grammar (HPSG) enjoys a uniform formalism representing rich contextual syntactic and even semantic meanings. This paper makes the first attempt to formulate a simplified HPSG by integrating constituent and dependency formal representations into head-driven phrase structure. Then two parsing algorithms are respectively proposed for two converted tree representations, division span and joint span. As HPSG encodes both constituent and dependency structure information, the proposed HPSG parsers may be regarded as a sort of joint decoder for both types of structures and thus are evaluated in terms of extracted or converted constituent and dependency parsing trees. Our parser achieves new state-of-the-art performance for both parsing tasks on Penn Treebank (PTB) and Chinese Penn Treebank, verifying the effectiveness of joint learning constituent and dependency structures. In details, we report 96.33 F1 of constituent parsing and 97.20\% UAS of dependency parsing on PTB.

PDF Abstract ACL 2019 PDF ACL 2019 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Constituency Parsing CTB5 Zhou etal. 2019 F1 score 89.40 # 8
Constituency Parsing Penn Treebank Head-Driven Phrase Structure Grammar Parsing (Joint) + XLNet F1 score 96.33 # 5
Dependency Parsing Penn Treebank HPSG Parser (Joint) + XLNet POS 97.3 # 5
UAS 97.20 # 4
LAS 95.72 # 5
Constituency Parsing Penn Treebank Head-Driven Phrase Structure Grammar Parsing (Joint) + BERT F1 score 95.84 # 10

Methods


No methods listed for this paper. Add relevant methods here