Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation

Sanghak Lee; Seungmin Seo; Byungkook Oh; Kyong Ho Lee; Donghoon Shin; Yeonsoo Lee

doi:10.1145/3340531.3412011

Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation

Sanghak Lee, Seungmin Seo, Byungkook Oh, Kyong Ho Lee, Donghoon Shin, Yeonsoo Lee

College of Computing

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

3 Citations (Scopus)

Abstract

This paper presents an efficient method of extracting n-ary relations from multiple sentences which is called Entity-path and Discourse relation-centric Relation Extractor (EDCRE). Unlike previous approaches, the proposed method focuses on an entity link, which consists of dependency edges between entities, and discourse relations between sentences. Specifically, the proposed model consists of two main sub-models. The first one encodes sentences with a higher weight on the entity link while considering the other edges with an attention mechanism. To consider various latent discourse relations between sentences, the second sub-model encodes discourse relations between adjacent sentences considering the contents of each sentence. Experiment results on the cross-sentence relation extraction dataset, PubMed, and the document-level relation extraction dataset, DocRED, show that the proposed model outperforms state-of-the-art methods of extracting relations across sentences. Furthermore, ablation study proves that both the two main sub-models have noticeable effect on the relation extraction task.

Original language	English
Title of host publication	CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management
Publisher	Association for Computing Machinery
Pages	705-714
Number of pages	10
ISBN (Electronic)	9781450368599
DOIs	https://doi.org/10.1145/3340531.3412011
Publication status	Published - 2020 Oct 19
Event	29th ACM International Conference on Information and Knowledge Management, CIKM 2020 - Virtual, Online, Ireland Duration: 2020 Oct 19 → 2020 Oct 23

Publication series

Name	International Conference on Information and Knowledge Management, Proceedings

Conference

Conference	29th ACM International Conference on Information and Knowledge Management, CIKM 2020
Country/Territory	Ireland
City	Virtual, Online
Period	20/10/19 → 20/10/23

Bibliographical note

Funding Information:
This work was supported by NCSOFT NLP Center. Kyong-Ho Lee is the corresponding author.

Publisher Copyright:
© 2020 ACM.

All Science Journal Classification (ASJC) codes

Business, Management and Accounting(all)
Decision Sciences(all)

Access to Document

10.1145/3340531.3412011

Cite this

Lee, S., Seo, S., Oh, B., Lee, K. H., Shin, D., & Lee, Y. (2020). Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation. In CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management (pp. 705-714). (International Conference on Information and Knowledge Management, Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3340531.3412011

Lee, Sanghak ; Seo, Seungmin ; Oh, Byungkook et al. / Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation. CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2020. pp. 705-714 (International Conference on Information and Knowledge Management, Proceedings).

@inproceedings{0353ac17935240849d008055ac4b3e32,

title = "Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation",

abstract = "This paper presents an efficient method of extracting n-ary relations from multiple sentences which is called Entity-path and Discourse relation-centric Relation Extractor (EDCRE). Unlike previous approaches, the proposed method focuses on an entity link, which consists of dependency edges between entities, and discourse relations between sentences. Specifically, the proposed model consists of two main sub-models. The first one encodes sentences with a higher weight on the entity link while considering the other edges with an attention mechanism. To consider various latent discourse relations between sentences, the second sub-model encodes discourse relations between adjacent sentences considering the contents of each sentence. Experiment results on the cross-sentence relation extraction dataset, PubMed, and the document-level relation extraction dataset, DocRED, show that the proposed model outperforms state-of-the-art methods of extracting relations across sentences. Furthermore, ablation study proves that both the two main sub-models have noticeable effect on the relation extraction task.",

author = "Sanghak Lee and Seungmin Seo and Byungkook Oh and Lee, {Kyong Ho} and Donghoon Shin and Yeonsoo Lee",

note = "Funding Information: This work was supported by NCSOFT NLP Center. Kyong-Ho Lee is the corresponding author. Publisher Copyright: {\textcopyright} 2020 ACM.; 29th ACM International Conference on Information and Knowledge Management, CIKM 2020 ; Conference date: 19-10-2020 Through 23-10-2020",

year = "2020",

month = oct,

day = "19",

doi = "10.1145/3340531.3412011",

language = "English",

series = "International Conference on Information and Knowledge Management, Proceedings",

publisher = "Association for Computing Machinery",

pages = "705--714",

booktitle = "CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management",

}

Lee, S, Seo, S, Oh, B, Lee, KH, Shin, D & Lee, Y 2020, Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation. in CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, Association for Computing Machinery, pp. 705-714, 29th ACM International Conference on Information and Knowledge Management, CIKM 2020, Virtual, Online, Ireland, 20/10/19. https://doi.org/10.1145/3340531.3412011

Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation. / Lee, Sanghak; Seo, Seungmin; Oh, Byungkook et al.
CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2020. p. 705-714 (International Conference on Information and Knowledge Management, Proceedings).

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

TY - GEN

T1 - Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation

AU - Lee, Sanghak

AU - Seo, Seungmin

AU - Oh, Byungkook

AU - Lee, Kyong Ho

AU - Shin, Donghoon

AU - Lee, Yeonsoo

PY - 2020/10/19

Y1 - 2020/10/19

N2 - This paper presents an efficient method of extracting n-ary relations from multiple sentences which is called Entity-path and Discourse relation-centric Relation Extractor (EDCRE). Unlike previous approaches, the proposed method focuses on an entity link, which consists of dependency edges between entities, and discourse relations between sentences. Specifically, the proposed model consists of two main sub-models. The first one encodes sentences with a higher weight on the entity link while considering the other edges with an attention mechanism. To consider various latent discourse relations between sentences, the second sub-model encodes discourse relations between adjacent sentences considering the contents of each sentence. Experiment results on the cross-sentence relation extraction dataset, PubMed, and the document-level relation extraction dataset, DocRED, show that the proposed model outperforms state-of-the-art methods of extracting relations across sentences. Furthermore, ablation study proves that both the two main sub-models have noticeable effect on the relation extraction task.

AB - This paper presents an efficient method of extracting n-ary relations from multiple sentences which is called Entity-path and Discourse relation-centric Relation Extractor (EDCRE). Unlike previous approaches, the proposed method focuses on an entity link, which consists of dependency edges between entities, and discourse relations between sentences. Specifically, the proposed model consists of two main sub-models. The first one encodes sentences with a higher weight on the entity link while considering the other edges with an attention mechanism. To consider various latent discourse relations between sentences, the second sub-model encodes discourse relations between adjacent sentences considering the contents of each sentence. Experiment results on the cross-sentence relation extraction dataset, PubMed, and the document-level relation extraction dataset, DocRED, show that the proposed model outperforms state-of-the-art methods of extracting relations across sentences. Furthermore, ablation study proves that both the two main sub-models have noticeable effect on the relation extraction task.

UR - http://www.scopus.com/inward/record.url?scp=85095864087&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85095864087&partnerID=8YFLogxK

U2 - 10.1145/3340531.3412011

DO - 10.1145/3340531.3412011

M3 - Conference contribution

AN - SCOPUS:85095864087

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 705

EP - 714

BT - CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management

PB - Association for Computing Machinery

T2 - 29th ACM International Conference on Information and Knowledge Management, CIKM 2020

Y2 - 19 October 2020 through 23 October 2020

ER -

Lee S, Seo S, Oh B, Lee KH, Shin D, Lee Y. Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation. In CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2020. p. 705-714. (International Conference on Information and Knowledge Management, Proceedings). doi: 10.1145/3340531.3412011

Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this