基于小句复合体的中文机器阅读理解研究(Machine Reading Comprehension Based on Clause Complex)

Ruiqi Wang (王瑞琦), Zhiyong Luo (罗智勇), Xiang Liu (刘祥), Rui Han (韩瑞昉), Shuxin Li (李舒馨)


Abstract
机器阅读理解任务要求机器根据篇章文本回答相关问题。本文以抽取式机器阅读理解为例,重点考察当问题的线索要素与答案在篇章文本中跨越多个标点句时的阅读理解问题。本文将小句复合体结构自动分析任务与机器阅读理解任务融合,利用小句复合体中跨标点句话头札话体共享关系,来化简机器阅读理解任务的难度;并设计与实现了基于小句复合体的机器阅读理解模型。实验结果表明:在问题线索要素与答案跨越多个标点句时,答案抽取的精确匹配率(EM)相对于基准模型提升了3.49%,模型整体的精确匹配率提升了3.26%。
Anthology ID:
2021.ccl-1.65
Volume:
Proceedings of the 20th Chinese National Conference on Computational Linguistics
Month:
August
Year:
2021
Address:
Huhhot, China
Editors:
Sheng Li (李生), Maosong Sun (孙茂松), Yang Liu (刘洋), Hua Wu (吴华), Kang Liu (刘康), Wanxiang Che (车万翔), Shizhu He (何世柱), Gaoqi Rao (饶高琦)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
723–735
Language:
Chinese
URL:
https://aclanthology.org/2021.ccl-1.65
DOI:
Bibkey:
Cite (ACL):
Ruiqi Wang, Zhiyong Luo, Xiang Liu, Rui Han, and Shuxin Li. 2021. 基于小句复合体的中文机器阅读理解研究(Machine Reading Comprehension Based on Clause Complex). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 723–735, Huhhot, China. Chinese Information Processing Society of China.
Cite (Informal):
基于小句复合体的中文机器阅读理解研究(Machine Reading Comprehension Based on Clause Complex) (Wang et al., CCL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ccl-1.65.pdf