Two-level Word Class Categorization Model in Analytic Languages and Its Implications for POS Tagging in Modern Chinese Corpora

Two-level Word Class Categorization Model in Analytic Languages and Its Implications for POS Tagging in Modern Chinese Corpora Renqiang Wang Graduate School, Sichuan International Studies University, Chongqing 40031 wangrenqiang@sisu.edu.cn Changning Huang Department of Computer Science and Technology, Tsinghua University, Beijing 100084 cnhuang0908@126.com Abstract The study of word classes has a history of over 4000 years, and the word class problem in over 1000 analytic languages like Modern Chinese can be seen as the Goldbach Conjecture in linguistics. This paper first outlines the existing problems in the POS tagging of Modern Chinese corpora with a case study of 自信. Then it introduces the Two-level Word Class Categorization Model in analytic languages, which is based on the perspectives of language as a complex adaptive system and the nature of major parts of speech as propositional speech act functions. Finally, the implications of Two-level Word Class Categorization Model for POS tagging in Modern Chinese corpora are explored. 1 Introduction Categorization is a fundamental task in linguistics, and linguistic categories like word classes or parts of speech were considered as the study of “god particles” in language in the 36th Annual Conference of the German Linguistic Society held at the University of Marburg, Germany, in March, 2014. In natural language processing, part-of-speech tagging plays a key role. As pointed out by Rabbi (2012), “It is a significant pre-requisite for putting a human language on the engineering track.” The study of word classes has a history of over 4000 years, but the word class problem in over one thousand analytic languages like Modern Chinese, Modern English and Tongan can be seen as the Goldbach Conjecture in linguistics, which has witnessed several upsurges over the last century. Let's take the example of 自信 in Chinese. The first five editions of The Contemporary Chinese Dictionary (hereinafter called CCD) have almost the same treatment of 自信 with the only definition of 相 信 自 己 , which is obviously a verbal usage according to the definition metalanguage, though it is only in CCD5 published in 2005 that the lexeme is explicitly labeled as VERB: 【自信】 zìxìn 动 相信自己：～心 | ～能够完成这个任务。 In CCD6 published in 2012, however, PACLIC 29 1 29th Pacific Asia Conference on Language, Information and Computation pages 1 - 10 Shanghai, China, October 30 - November 1, 2015 Copyright 2015 by Renqiang Wang and Changning Huang we can see that 自信 is labeled as a multi-category lexeme belonging to VERB, NOUN and ADJECTIVE: 【自信】zìxìn ❶ 动 相信自己：～ 心 | ～能够完成这个任务。❷ 名 对自己的信心：不能失去～ | 工作 了几年之后，他更多了几分～。❸ 形 对自己 有信 心：他做 事总 是 很～。 In the second edition of The Grammatical knowledge-base of Contemporary Chinese — A Complete Specification (Yu et al., 2003), 自信 is specified only as VERB with the following examples, which illustrate its typical usages: ～心 | 他～自己能考取北京大学/ 我～能完成任务/～地说/在困难面前， 需要～ Then what about the POS tagging of 自信 in Chinese corpora? We downloaded all the concordance lines from the Modern Chinese Corpus developed by the China National Language and Character Working Committee (hereinafter called CN …

Content truncated to 500 words