Joint type inference on entities and relations via graph convolutional networks

Changzhi Sun; Yeyun Gong; Yuanbin Wu; Ming Gong; Daxing Jiang; Man Lan; Shiliang Sun; Nan Duan

Joint type inference on entities and relations via graph convolutional networks

Changzhi Sun
, Yeyun Gong
, Yuanbin Wu
, Ming Gong
, Daxing Jiang
, Man Lan
, Shiliang Sun
, Nan Duan

School of Computer Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

109 Scopus citations

Abstract

We develop a new paradigm for the task of joint entity relation extraction. It first identifies entity spans, then performs a joint inference on entity types and relation types. To tackle the joint type inference task, we propose a novel graph convolutional network (GCN) running on an entity-relation bipartite graph. By introducing a binary relation classification task, we are able to utilize the structure of entity-relation bipartite graph in a more efficient and interpretable way. Experiments on ACE05 show that our model outperforms existing joint models in entity performance and is competitive with the state-of-the-art in relation performance.

Original language	English
Title of host publication	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	1361-1370
Number of pages	10
ISBN (Electronic)	9781950737482
State	Published - 2020
Event	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Florence, Italy Duration: 28 Jul 2019 → 2 Aug 2019

Publication series

Name	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Country/Territory	Italy
City	Florence
Period	28/07/19 → 2/08/19

Cite this

Sun, C., Gong, Y., Wu, Y., Gong, M., Jiang, D., Lan, M., Sun, S., & Duan, N. (2020). Joint type inference on entities and relations via graph convolutional networks. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 1361-1370). (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

Sun, Changzhi ; Gong, Yeyun ; Wu, Yuanbin et al. / Joint type inference on entities and relations via graph convolutional networks. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. pp. 1361-1370 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

@inproceedings{506e9275ca93497fafad83a63b980c97,

title = "Joint type inference on entities and relations via graph convolutional networks",

abstract = "We develop a new paradigm for the task of joint entity relation extraction. It first identifies entity spans, then performs a joint inference on entity types and relation types. To tackle the joint type inference task, we propose a novel graph convolutional network (GCN) running on an entity-relation bipartite graph. By introducing a binary relation classification task, we are able to utilize the structure of entity-relation bipartite graph in a more efficient and interpretable way. Experiments on ACE05 show that our model outperforms existing joint models in entity performance and is competitive with the state-of-the-art in relation performance.",

author = "Changzhi Sun and Yeyun Gong and Yuanbin Wu and Ming Gong and Daxing Jiang and Man Lan and Shiliang Sun and Nan Duan",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2020",

language = "英语",

series = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "1361--1370",

booktitle = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

address = "澳大利亚",

}

Sun, C, Gong, Y, Wu, Y, Gong, M, Jiang, D, Lan, M, Sun, S & Duan, N 2020, Joint type inference on entities and relations via graph convolutional networks. in ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 1361-1370, 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019, Florence, Italy, 28/07/19.

Joint type inference on entities and relations via graph convolutional networks. / Sun, Changzhi; Gong, Yeyun; Wu, Yuanbin et al.
ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. p. 1361-1370 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Joint type inference on entities and relations via graph convolutional networks

AU - Sun, Changzhi

AU - Gong, Yeyun

AU - Wu, Yuanbin

AU - Gong, Ming

AU - Jiang, Daxing

AU - Lan, Man

AU - Sun, Shiliang

AU - Duan, Nan

PY - 2020

Y1 - 2020

N2 - We develop a new paradigm for the task of joint entity relation extraction. It first identifies entity spans, then performs a joint inference on entity types and relation types. To tackle the joint type inference task, we propose a novel graph convolutional network (GCN) running on an entity-relation bipartite graph. By introducing a binary relation classification task, we are able to utilize the structure of entity-relation bipartite graph in a more efficient and interpretable way. Experiments on ACE05 show that our model outperforms existing joint models in entity performance and is competitive with the state-of-the-art in relation performance.

AB - We develop a new paradigm for the task of joint entity relation extraction. It first identifies entity spans, then performs a joint inference on entity types and relation types. To tackle the joint type inference task, we propose a novel graph convolutional network (GCN) running on an entity-relation bipartite graph. By introducing a binary relation classification task, we are able to utilize the structure of entity-relation bipartite graph in a more efficient and interpretable way. Experiments on ACE05 show that our model outperforms existing joint models in entity performance and is competitive with the state-of-the-art in relation performance.

UR - https://www.scopus.com/pages/publications/85082507441

M3 - 会议稿件

AN - SCOPUS:85082507441

T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

SP - 1361

EP - 1370

BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Sun C, Gong Y, Wu Y, Gong M, Jiang D, Lan M et al. Joint type inference on entities and relations via graph convolutional networks. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 1361-1370. (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

Joint type inference on entities and relations via graph convolutional networks

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this