Head-Driven Phrase Structure Grammar Parsing on Penn Treebank

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2396–2408 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 2396 Head-Driven Phrase Structure Grammar Parsing on Penn Treebank Junru Zhou and Hai Zhao∗ Department of Computer Science and Engineering Key Lab of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University, Shanghai, China zhoujunru@sjtu.edu.cn, zhaohai@cs.sjtu.edu.cn Abstract Head-driven phrase structure grammar (HPSG) enjoys a uniform formalism repre- senting 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 de- pendency 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 95.84 F1 of constituent parsing and 97.00% UAS of dependency parsing on PTB. 1 Introduction Head-driven phrase structure grammar (HPSG) is a highly lexicalized, constraint-based grammar de- veloped by (Pollard and Sag, 1994). As opposed to dependency grammar, HPSG is the immediate successor of generalized phrase structure gram- mar. HPSG divides language symbols into categories of different types, such as vocabulary, phrases, etc. Each category has different grammar letter infor- mation. The complete language symbol which is a complex type feature structure represented by ∗ Corresponding author. This paper was partially sup- ported by National Key Research and Development Program of China (No. 2017YFB0304100) and key projects of Nat- ural Science Foundation of China (No. U1836222 and No. 61733011) Kim gives Sandy books VP S NNP VBZ NNP NP NNS NP NP (a) Constituent Kim gives Sandy books ROOT NNP VBZ NNP NNS (b) Dependency Sandy 2 books 3 SYNSEM|LOC|CAT HEAD 4 SUBCAT< 1 > HEAD 4 SYNSEM|LOC|CAT HEAD 4 verb[fin] SUBCAT< 1 NP, 2 NP, 3 NP > SUBCAT < > SYNSEM|LOC|CAT 1 gives Kim (=S[fin]) (=VP[fin]) C H H C C (c) HPSG Figure 1: Constituent, dependency and HPSG trees. attribute value matrices (AVMs) includes phono- logical, syntactic, and semantic properties, the va- lence of the word and interrelationship between various components of the phrase structure. Meanwhile, the constituent structure of HPSG follows the HEAD FEATURE PRINCIPLE (HFP) (Pollard and Sag, 1994): “the head value of any headed phrase is structure-shared with the HEAD value of the head daughter. The effect of the HFP is to guarantee that headed phrases really are pro- jections of their head daughter” (p. 34). Constituent and dependency are two typical syntactic structure representation forms, which have been well studied from both linguistic and computational perspective (Chomsky, 1981; Bres- nan et al., 2015). …

Content truncated to 500 words