Event Temporal Relation Extraction with Attention Mechanism and Graph Neural Network

被引:34
作者
Xu, Xiaoliang [1 ]
Gao, Tong [1 ]
Wang, Yuxiang [1 ]
Xuan, Xinle [2 ]
机构
[1] Hangzhou Dianzi Univ, Dept Comp Sci & Engn, Hangzhou 310018, Peoples R China
[2] Hangzhou Sanhui Digital Informat Technol Co Ltd, Hangzhou 310018, Peoples R China
基金
中国国家自然科学基金;
关键词
temporal relation extraction; neural network; attention mechanism; graph attention network;
D O I
10.26599/TST.2020.9010063
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Event temporal relation extraction is an important part of natural language processing. Many models are being used in this task with the development of deep learning. However, most of the existing methods cannot accurately obtain the degree of association between different tokens and events, and event-related information cannot be effectively integrated. In this paper, we propose an event information integration model that integrates event information through multilayer bidirectional long short-term memory (Bi-LSTM) and attention mechanism. Although the above scheme can improve the extraction performance, it can still be further optimized. To further improve the performance of the previous scheme, we propose a novel relational graph attention network that incorporates edge attributes. In this approach, we first build a semantic dependency graph through dependency parsing, model a semantic graph that considers the edges' attributes by using top-k attention mechanisms to learn hidden semantic contextual representations, and finally predict event temporal relations. We evaluate proposed models on the TimeBank-Dense dataset. Compared to previous baselines, the Micro-F1 scores obtained by our models improve by 3.9% and 14.5%, respectively.
引用
收藏
页码:79 / 90
页数:12
相关论文
共 37 条
[1]  
[Anonymous], 2016, ADV NEURAL INFORM PR
[2]  
[Anonymous], 2017, ARXIV PREPRINT ARXIV
[3]  
[Anonymous], 2016, P COLING 2016 26 INT
[4]  
Busbridge D., 2019, ARXIV PREPRINT ARXIV
[5]  
Chambers N., 2014, Trans. Assoc. Comput. Linguistics, V2, P273, DOI DOI 10.1162/tacl_a_00182
[6]  
Chambers Nathanael., 2013, Navytime: Event and time ordering from raw text
[7]  
Chambers Nathanael., 2007, P 45 ANN M ASS COMPU, P173, DOI DOI 10.3115/1557769.1557820
[8]   Classifying Temporal Relations by Bidirectional LSTM over Dependency Paths [J].
Cheng, Fei ;
Miyao, Yusuke .
PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 2, 2017, :1-6
[9]  
Choubey PK., 2017, P 2017 C EMPIRICAL M, P1796
[10]  
Derczynski L., 2012, ARXIV PREPRINT ARXIV