基于信息交互增强的时序关系联合识别(Joint Recognition of Temporal Relation Based on Information Interaction Enhancement)

Qianying Dai (戴倩颖), Fang Kong (孔芳)


Abstract
时序关系识别是信息抽取领域的一个重要分支,对文本理解发挥着关键作用。按照关联对象的不同,时序关系分为三大类:事件对(E-E)间的时序关系,事件与时间表达式间(E-T)的时序关系,事件与文档建立时间(E-D)间的时序关系。不同关系类型孤立识别的方法忽视了其间隐含的关联信息,针对这一问题构建了基于信息交互增强的时序关系联合识别模型。通过在不同神经网络层之间共享参数实现E-E与E-T时序关系的语义交流,利用两者的潜在联系提高识别精度。在Time-Bank Dense语料上的一系列实验表明,该方法优于现有的大多数神经网络方法。
Anthology ID:
2021.ccl-1.72
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:
803–812
Language:
Chinese
URL:
https://aclanthology.org/2021.ccl-1.72
DOI:
Bibkey:
Cite (ACL):
Qianying Dai and Fang Kong. 2021. 基于信息交互增强的时序关系联合识别(Joint Recognition of Temporal Relation Based on Information Interaction Enhancement). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 803–812, Huhhot, China. Chinese Information Processing Society of China.
Cite (Informal):
基于信息交互增强的时序关系联合识别(Joint Recognition of Temporal Relation Based on Information Interaction Enhancement) (Dai & Kong, CCL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ccl-1.72.pdf