SaGCN: Structure-Aware Graph Convolution Network for Document-Level Relation Extraction

被引：0

作者：

Yang, Shuangji ^{[1
,3
]}

Zhang, Taolin ^{[2
,3
]}

Su, Danning ^{[2
]}

Hu, Nan ^{[1
,3
]}

Nong, Wei ^{[1
,3
]}

He, Xiaofeng ^{[1
,3
]}

机构：

[1] East China Normal Univ, Sch Comp Sci & Technol, Shanghai, Peoples R China

[2] East China Normal Univ, Sch Software Engn, Shanghai, Peoples R China

[3] Shanghai Key Lab Trustworthy Comp, Shanghai, Peoples R China

来源：

ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2021, PT III | 2021年 / 12714卷

关键词：

Document-level relation extraction; Structure-aware information injection; Graph neural network;

D O I：

10.1007/978-3-030-75768-7_30

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Document-level Relation Extraction(DocRE) aims at extracting semantic relations among entities in documents. However, current models lack long-range dependency information and the reasoning ability to extract essential structure information from the text. In this paper, we propose SaGCN, a Structure-aware Graph Convolution Network, extracting relation with explicit and implicit dependency structure. Specifically, we generate the implicit graph by sampling from a discrete and continuous distribution, then dynamically fuse the implicit soft structure with the dependent hard structure. Experimental results of SaGCN outperform the performance achieved by current state-of-the-art various baseline models on the DocRED dataset.

引用

页码：377 / 389

页数：13

共 33 条

[1] [Anonymous], 2019, 57 ANN M ASS COMP
[2] Bastings Joost, INTERPRETABLE NEURAL
[3] Beck D, 2018, PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1, P273
[4] Christopoulou F, 2019, 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019), P4925
[5] Culotta A., 2004, P 42 ANN M ASS COMPU, p423, DOI [10.3115/1218955.1219009, DOI 10.3115/1218955.1219009]
[6] Devlin Jacob, 2018, ACL
[7] Glorot X., 2011, JMLR WORKSHOP C P, P315
[8] Graves A, 2012, STUD COMPUT INTELL, V385, P1, DOI [10.1007/978-3-642-24797-2, 10.1162/neco.1997.9.1.1]
[9] Guo ZJ, 2020, PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P3651
[10] Guo ZJ, 2019, 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), P241

← 1 2 3 4 →