汉语语义构词的资源建设与计算评估(Construction of Chinese Semantic Word-Formation and its Computing Applications)

Yue Wang (王悦), Yang Liu (刘扬), Qiliang Liang (梁启亮), Hansi Wang (王涵思)


Abstract
“汉语是一种意合型语言,汉语中语素的构词方式与规律是描述、理解词义的重要因素。关于语素构词的方式,语言学界有语法构词与语义构词这两种观点,其中,语义构词对语素间关系的表达更为深入。本文采取语义构词的路线,基于语言学视角,考虑汉语构词特点,提出了一套面向计算的语义构词结构体系,通过随机森林自动标注与人工校验相结合的方式,构建汉语语义构词知识库,并在词义生成的任务上对该资源进行计算评估。实验取得了良好的结果,基于语义构词知识库的词义生成BLEU值达25.07,较此前的语法构词提升了3.17%,初步验证了这种知识表示方法的有效性。该知识表示方法与资源建设将为人文领域和信息处理等多方面的应用提供新的思路与方案。”
Anthology ID:
2023.ccl-1.40
Volume:
Proceedings of the 22nd Chinese National Conference on Computational Linguistics
Month:
August
Year:
2023
Address:
Harbin, China
Editors:
Maosong Sun, Bing Qin, Xipeng Qiu, Jing Jiang, Xianpei Han
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
456–465
Language:
Chinese
URL:
https://aclanthology.org/2023.ccl-1.40
DOI:
Bibkey:
Cite (ACL):
Yue Wang, Yang Liu, Qiliang Liang, and Hansi Wang. 2023. 汉语语义构词的资源建设与计算评估(Construction of Chinese Semantic Word-Formation and its Computing Applications). In Proceedings of the 22nd Chinese National Conference on Computational Linguistics, pages 456–465, Harbin, China. Chinese Information Processing Society of China.
Cite (Informal):
汉语语义构词的资源建设与计算评估(Construction of Chinese Semantic Word-Formation and its Computing Applications) (Wang et al., CCL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.ccl-1.40.pdf