Head-Driven Phrase Structure Grammar Parsing on Penn Treebank

Abstract

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.

Indonesian Short Essay Scoring Using Transfer Learning Dependency Tree LSTM

“…The grammatical structure can establish with constituency structures and dependency structures [14]. In constituency structures, the grammatical structure of sentences is obtained by grouping word into nested constituencies [15]. Another case with dependency structure, the grammatical structure is contracted by seeking each word relational [15].…”

“…In constituency structures, the grammatical structure of sentences is obtained by grouping word into nested constituencies [15]. Another case with dependency structure, the grammatical structure is contracted by seeking each word relational [15]. Dependency parsing is an analysis that based on structural dependency syntax in the sentences [16].…”

A Speech-to-Knowledge-Graph Construction System

“…The knowledge graph construction from a text consists of the following 5 steps: Preprocessing. Special characters in the extracted text are removed and BERT-based [Devlin et al, 2019] sequence tagging models are used to perform Chinese word segmentation, part-of-speech analysis, and Head-Driven Phrase Structure Grammar Parsing [Zhou and Zhao, 2019] is reproduced for dependency tree analysis on the extracted text. Models are trained on Penn Chinese Treebank dataset 3 .…”

Tagging and Parsing of Multidomain Collections

“…Currently the best performing dependency parsers for English are immediate successors of HPSG model introduced in [24]. The most important feature of this family of parsers is joint learning on dependency and constituency trees.…”