Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction

Junyoung Son; Jinsung Kim; Jungwoo Lim; Yoonna Jang; Heuiseok Lim

Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction

Junyoung Son, Jinsung Kim, Jungwoo Lim, Yoonna Jang, Heuiseok Lim

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

Abstract

Cross-document relation extraction (CodRED) task aims to infer the relation between two entities mentioned in different documents within a reasoning path. Previous studies have concentrated on merely capturing implicit relations between the entities. However, humans usually utilize explicit information chains such as hyperlinks or additional searches to find the relations between two entities. Inspired by this, we propose Path wIth expLOraTion (PILOT) that provides the enhanced reasoning path by exploring the explicit clue information within the documents. PILOT finds the bridging entities that directly guide the model with paths between the given entities and then employs them as stepstones to navigate desirable paths. We show that models with PILOT outperform the baselines in the CodRED task. Furthermore, we provide a variety of analyses to verify the validity of the reasoning paths constructed through PILOT, including evaluations using large language models such as ChatGPT.

Original language	English
Title of host publication	Findings of the Association for Computational Linguistics
Subtitle of host publication	EMNLP 2023
Publisher	Association for Computational Linguistics (ACL)
Pages	6755-6761
Number of pages	7
ISBN (Electronic)	9798891760615
Publication status	Published - 2023
Event	2023 Findings of the Association for Computational Linguistics: EMNLP 2023 - Singapore, Singapore Duration: 2023 Dec 6 → 2023 Dec 10

Publication series

Name	Findings of the Association for Computational Linguistics: EMNLP 2023

Conference

Conference	2023 Findings of the Association for Computational Linguistics: EMNLP 2023
Country/Territory	Singapore
City	Singapore
Period	23/12/6 → 23/12/10

Bibliographical note

Publisher Copyright:
© 2023 Association for Computational Linguistics.

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Information Systems
Language and Linguistics
Linguistics and Language

Cite this

Son, J., Kim, J., Lim, J., Jang, Y., & Lim, H. (2023). Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2023 (pp. 6755-6761). (Findings of the Association for Computational Linguistics: EMNLP 2023). Association for Computational Linguistics (ACL).

Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction. / Son, Junyoung; Kim, Jinsung; Lim, Jungwoo et al.
Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics (ACL), 2023. p. 6755-6761 (Findings of the Association for Computational Linguistics: EMNLP 2023).

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

Son, J, Kim, J, Lim, J, Jang, Y & Lim, H 2023, Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction. in Findings of the Association for Computational Linguistics: EMNLP 2023. Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics (ACL), pp. 6755-6761, 2023 Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, Singapore, 23/12/6.

Son, Junyoung ; Kim, Jinsung ; Lim, Jungwoo et al. / Explore the Way : Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction. Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics (ACL), 2023. pp. 6755-6761 (Findings of the Association for Computational Linguistics: EMNLP 2023).

@inproceedings{c7bf4dc4fb3f4c5c89726a968e43f8ed,

title = "Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction",

abstract = "Cross-document relation extraction (CodRED) task aims to infer the relation between two entities mentioned in different documents within a reasoning path. Previous studies have concentrated on merely capturing implicit relations between the entities. However, humans usually utilize explicit information chains such as hyperlinks or additional searches to find the relations between two entities. Inspired by this, we propose Path wIth expLOraTion (PILOT) that provides the enhanced reasoning path by exploring the explicit clue information within the documents. PILOT finds the bridging entities that directly guide the model with paths between the given entities and then employs them as stepstones to navigate desirable paths. We show that models with PILOT outperform the baselines in the CodRED task. Furthermore, we provide a variety of analyses to verify the validity of the reasoning paths constructed through PILOT, including evaluations using large language models such as ChatGPT.",

author = "Junyoung Son and Jinsung Kim and Jungwoo Lim and Yoonna Jang and Heuiseok Lim",

note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 2023 Findings of the Association for Computational Linguistics: EMNLP 2023 ; Conference date: 06-12-2023 Through 10-12-2023",

year = "2023",

language = "English",

series = "Findings of the Association for Computational Linguistics: EMNLP 2023",

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

pages = "6755--6761",

booktitle = "Findings of the Association for Computational Linguistics",

}

TY - GEN

T1 - Explore the Way

T2 - 2023 Findings of the Association for Computational Linguistics: EMNLP 2023

AU - Son, Junyoung

AU - Kim, Jinsung

AU - Lim, Jungwoo

AU - Jang, Yoonna

AU - Lim, Heuiseok

PY - 2023

Y1 - 2023

N2 - Cross-document relation extraction (CodRED) task aims to infer the relation between two entities mentioned in different documents within a reasoning path. Previous studies have concentrated on merely capturing implicit relations between the entities. However, humans usually utilize explicit information chains such as hyperlinks or additional searches to find the relations between two entities. Inspired by this, we propose Path wIth expLOraTion (PILOT) that provides the enhanced reasoning path by exploring the explicit clue information within the documents. PILOT finds the bridging entities that directly guide the model with paths between the given entities and then employs them as stepstones to navigate desirable paths. We show that models with PILOT outperform the baselines in the CodRED task. Furthermore, we provide a variety of analyses to verify the validity of the reasoning paths constructed through PILOT, including evaluations using large language models such as ChatGPT.

AB - Cross-document relation extraction (CodRED) task aims to infer the relation between two entities mentioned in different documents within a reasoning path. Previous studies have concentrated on merely capturing implicit relations between the entities. However, humans usually utilize explicit information chains such as hyperlinks or additional searches to find the relations between two entities. Inspired by this, we propose Path wIth expLOraTion (PILOT) that provides the enhanced reasoning path by exploring the explicit clue information within the documents. PILOT finds the bridging entities that directly guide the model with paths between the given entities and then employs them as stepstones to navigate desirable paths. We show that models with PILOT outperform the baselines in the CodRED task. Furthermore, we provide a variety of analyses to verify the validity of the reasoning paths constructed through PILOT, including evaluations using large language models such as ChatGPT.

UR - http://www.scopus.com/inward/record.url?scp=85183304380&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85183304380

T3 - Findings of the Association for Computational Linguistics: EMNLP 2023

SP - 6755

EP - 6761

BT - Findings of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

Y2 - 6 December 2023 through 10 December 2023

ER -

Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this