Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Head-Driven Phrase Structure Grammar Parsing on Penn Treebank

About

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.

Junru Zhou, Hai Zhao• 2019

Related benchmarks

TaskDatasetResultRank
Constituent ParsingPTB (test)
F196.33
127
Dependency ParsingChinese Treebank (CTB) (test)
UAS93.24
99
Dependency ParsingPenn Treebank (PTB) (test)
LAS95.72
80
Phrase-structure parsingPTB (§23)
F1 Score95.8
56
Constituent ParsingCTB (test)
F1 Score92.55
45
Constituency ParsingWSJ Penn Treebank (test)
F1 Score95.84
27
Constituency ParsingCTB 5.1 (test)
F1 Score92.18
25
Dependency ParsingPTB
UAS97.2
24
Constituency ParsingCTB 5.0 (test)
F1 Score92.18
19
ParsingPTB (test)
Sents/sec226.3
17
Showing 10 of 15 rows

Other info

Code

Follow for update