基于组块分析的汉语块依存语法(Chinese Chunk-Based Dependency Grammar)

Qingqing Qian (钱青青), Chengwen Wang (王诚文), Gaoqi Rao (饶高琦), Endong Xun (荀恩东)


Abstract
基于词单元的经典依存语法在面向中文的句子分析中遇到诸多汉语特性引起的困难。为此,本文提出汉语的块依存语法,以谓词为核心,以组块为研究对象,在句内和句间寻找谓词所支配的组块,构建句群级别的句法分析框架。这一操作不仅仅是提升叶子节点的语言单位,而且还针对汉语语义特点进行了分析方式和分析规则上的创新,能够较好地解决微观层次的逻辑结构知识,并为中观论元知识和宏观篇章知识打好铺垫。本文主要介绍了块依存语法理念、表示、分析方法及特点,并简要介绍了块依存树库的构建情况。截至目前为止,树库规模为187万字符(超过4万复句、10万小句),其中包含67%新闻文本和32%百科文本。
Anthology ID:
2020.ccl-1.12
Volume:
Proceedings of the 19th Chinese National Conference on Computational Linguistics
Month:
October
Year:
2020
Address:
Haikou, China
Editors:
Maosong Sun (孙茂松), Sujian Li (李素建), Yue Zhang (张岳), Yang Liu (刘洋)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
117–127
Language:
Chinese
URL:
https://aclanthology.org/2020.ccl-1.12
DOI:
Bibkey:
Cite (ACL):
Qingqing Qian, Chengwen Wang, Gaoqi Rao, and Endong Xun. 2020. 基于组块分析的汉语块依存语法(Chinese Chunk-Based Dependency Grammar). In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 117–127, Haikou, China. Chinese Information Processing Society of China.
Cite (Informal):
基于组块分析的汉语块依存语法(Chinese Chunk-Based Dependency Grammar) (Qian et al., CCL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.ccl-1.12.pdf