Parsing Chinese Sentences with Grammatical Relations

Parsing Chinese Sentences with Grammatical Relations Weiwei Sun Peking University Institute of Computer Science and Technology and Center for Chinese Linguistics ws@pku.edu.cn Yufei Chen Peking University Institute of Computer Science and Technology yufei.chen@pku.edu.cn Xiaojun Wan Peking University Institute of Computer Science and Technology wanxiaojun@pku.edu.cn Meichun Liu City University of Hong Kong Department of Linguistics and Translation meichliu@cityu.edu.hk We report our work on building linguistic resources and data-driven parsers in the grammatical relation (GR) analysis for Mandarin Chinese. Chinese, as an analytic language, encodes gram- matical information in a highly configurational rather than morphological way. Accordingly, it is possible and reasonable to represent almost all grammatical relations as bilexical dependencies. In this work, we propose to represent grammatical information using general directed dependency graphs. Both only-local and rich long-distance dependencies are explicitly represented. To create high-quality annotations, we take advantage of an existing TreeBank, namely, Chinese TreeBank (CTB), which is grounded on the Government and Binding theory. We define a set of linguistic rules to explore CTB’s implicit phrase structural information and build deep dependency graphs. The reliability of this linguistically motivated GR extraction procedure is highlighted by manual Submission received: 23 November 2017; revised version received: 19 September 2018; accepted for publication: 19 November 2018. doi:10.1162/COLI a 00343 © 2019 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Computational Linguistics Volume 45, Number 1 evaluation. Based on the converted corpus, data-driven, including graph- and transition-based, models are explored for Chinese GR parsing. For graph-based parsing, a new perspective, graph merging, is proposed for building flexible dependency graphs: constructing complex graphs via constructing simple subgraphs. Two key problems are discussed in this perspective: (1) how to decompose a complex graph into simple subgraphs, and (2) how to combine subgraphs into a coherent complex graph. For transition-based parsing, we introduce a neural parser based on a list-based transition system. We also discuss several other key problems, including dynamic oracle and beam search for neural transition-based parsing. Evaluation gauges how successful GR parsing for Chinese can be by applying data-driven models. The empirical analysis suggests several directions for future study. 1. Introduction Dependency grammar is a longstanding tradition that determines syntactic structures on the basis of word-to-word connections. It names a family of approaches to the lin- guistic analysis that all share a commitment to the typed relations between ordered pairs of words. Usually, dependencies represent various grammatical relations (GRs), which are exemplified in traditional grammars by the notions of subject, direct/indirect object, etc., and therefore encode rich syntactic information of natural language sentences in an explicit way. In recent years, parsing a sentence to a dependency representation has been well studied and widely applied to many Natural Language Processing (NLP) tasks, for example, Information Extraction and Machine Translation. In particular, the data-driven approaches have made great progress during the past two decades (K¨ubler, McDonald, and Nivre 2009; Koo et al. 2010; Pitler, Kannan, and Marcus 2013; Chen and Manning 2014; Weiss et al. 2015; …

Content truncated to 500 words