融合全局和局部信息的汉语宏观篇章结构识别(Combining Global and Local Information to Recognize Chinese Macro Discourse Structure)

Yaxin Fan (范亚鑫), Feng Jiang (蒋峰), Xiaomin Chu (褚晓敏), Peifeng Li (李培峰), Qiaoming Zhu (朱巧明)


Abstract
作为宏观篇章分析中的基础任务,篇章结构识别任务的目的是识别相邻篇章单元之间的结构,并层次化构建篇章结构树。已有的工作只考虑局部的结构和语义信息或只考虑全局信息。因此,本文提出了一种融合全局和局部信息的指针网络模型,该模型在考虑全局的语义信息同时,又考虑局部段落间的语义关系密切程度,从而有效地提高宏观篇章结构识别的能力。在汉语宏观篇章树库(MCDTB)的实验结果表明,本文所提出的模型性能优于目前性能最好的模型。
Anthology ID:
2020.ccl-1.18
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:
183–194
Language:
Chinese
URL:
https://aclanthology.org/2020.ccl-1.18
DOI:
Bibkey:
Cite (ACL):
Yaxin Fan, Feng Jiang, Xiaomin Chu, Peifeng Li, and Qiaoming Zhu. 2020. 融合全局和局部信息的汉语宏观篇章结构识别(Combining Global and Local Information to Recognize Chinese Macro Discourse Structure). In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 183–194, Haikou, China. Chinese Information Processing Society of China.
Cite (Informal):
融合全局和局部信息的汉语宏观篇章结构识别(Combining Global and Local Information to Recognize Chinese Macro Discourse Structure) (Fan et al., CCL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.ccl-1.18.pdf