GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction

Junyoung Son; Jinsung Kim; Jungwoo Lim; Heuiseok Lim

GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction

Junyoung Son, Jinsung Kim, Jungwoo Lim, Heuiseok Lim

Research output: Contribution to journal › Conference article › peer-review

Abstract

The dialogue-based relation extraction (DialogRE) task aims to predict the relations between argument pairs that appear in dialogue. Most previous studies utilize fine-tuning pre-trained language models (PLMs) only with extensive features to supplement the low information density of the dialogue by multiple speakers. To effectively exploit inherent knowledge of PLMs without extra layers and consider scattered semantic cues on the relation between the arguments, we propose a Guiding model with RelAtional Semantics using Prompt (GRASP). We adopt a prompt-based fine-tuning approach and capture relational semantic clues of a given dialogue with 1) an argument-aware prompt marker strategy and 2) the relational clue detection task. In the experiments, GRASP achieves state-of-the-art performance in terms of both F1 and F1_c scores on a DialogRE dataset even though our method only leverages PLMs without adding any extra layers.

Original language	English
Pages (from-to)	412-423
Number of pages	12
Journal	Proceedings - International Conference on Computational Linguistics, COLING
Volume	29
Issue number	1
Publication status	Published - 2022
Event	29th International Conference on Computational Linguistics, COLING 2022 - Gyeongju, Korea, Republic of Duration: 2022 Oct 12 → 2022 Oct 17

Bibliographical note

Funding Information:
This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques), the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2022-2018-0-01405) supervised by the IITP, and the MSIT, Korea, under the ICT Creative Consilience program (IITP-2022-2020-0-01819) supervised by the IITP.

Publisher Copyright:
© 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Theoretical Computer Science

Cite this

@article{fdf377f0643d41409b9c018bf3bee9de,

title = "GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction",

abstract = "The dialogue-based relation extraction (DialogRE) task aims to predict the relations between argument pairs that appear in dialogue. Most previous studies utilize fine-tuning pre-trained language models (PLMs) only with extensive features to supplement the low information density of the dialogue by multiple speakers. To effectively exploit inherent knowledge of PLMs without extra layers and consider scattered semantic cues on the relation between the arguments, we propose a Guiding model with RelAtional Semantics using Prompt (GRASP). We adopt a prompt-based fine-tuning approach and capture relational semantic clues of a given dialogue with 1) an argument-aware prompt marker strategy and 2) the relational clue detection task. In the experiments, GRASP achieves state-of-the-art performance in terms of both F1 and F1c scores on a DialogRE dataset even though our method only leverages PLMs without adding any extra layers.",

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

note = "Funding Information: This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques), the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2022-2018-0-01405) supervised by the IITP, and the MSIT, Korea, under the ICT Creative Consilience program (IITP-2022-2020-0-01819) supervised by the IITP. Publisher Copyright: {\textcopyright} 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.; 29th International Conference on Computational Linguistics, COLING 2022 ; Conference date: 12-10-2022 Through 17-10-2022",

year = "2022",

language = "English",

volume = "29",

pages = "412--423",

journal = "Proceedings - International Conference on Computational Linguistics, COLING",

issn = "2951-2093",

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

number = "1",

}

TY - JOUR

T1 - GRASP

T2 - 29th International Conference on Computational Linguistics, COLING 2022

AU - Son, Junyoung

AU - Kim, Jinsung

AU - Lim, Jungwoo

AU - Lim, Heuiseok

N1 - Funding Information: This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques), the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2022-2018-0-01405) supervised by the IITP, and the MSIT, Korea, under the ICT Creative Consilience program (IITP-2022-2020-0-01819) supervised by the IITP. Publisher Copyright: © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

PY - 2022

Y1 - 2022

N2 - The dialogue-based relation extraction (DialogRE) task aims to predict the relations between argument pairs that appear in dialogue. Most previous studies utilize fine-tuning pre-trained language models (PLMs) only with extensive features to supplement the low information density of the dialogue by multiple speakers. To effectively exploit inherent knowledge of PLMs without extra layers and consider scattered semantic cues on the relation between the arguments, we propose a Guiding model with RelAtional Semantics using Prompt (GRASP). We adopt a prompt-based fine-tuning approach and capture relational semantic clues of a given dialogue with 1) an argument-aware prompt marker strategy and 2) the relational clue detection task. In the experiments, GRASP achieves state-of-the-art performance in terms of both F1 and F1c scores on a DialogRE dataset even though our method only leverages PLMs without adding any extra layers.

AB - The dialogue-based relation extraction (DialogRE) task aims to predict the relations between argument pairs that appear in dialogue. Most previous studies utilize fine-tuning pre-trained language models (PLMs) only with extensive features to supplement the low information density of the dialogue by multiple speakers. To effectively exploit inherent knowledge of PLMs without extra layers and consider scattered semantic cues on the relation between the arguments, we propose a Guiding model with RelAtional Semantics using Prompt (GRASP). We adopt a prompt-based fine-tuning approach and capture relational semantic clues of a given dialogue with 1) an argument-aware prompt marker strategy and 2) the relational clue detection task. In the experiments, GRASP achieves state-of-the-art performance in terms of both F1 and F1c scores on a DialogRE dataset even though our method only leverages PLMs without adding any extra layers.

UR - http://www.scopus.com/inward/record.url?scp=85152568388&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85152568388

SN - 2951-2093

VL - 29

SP - 412

EP - 423

JO - Proceedings - International Conference on Computational Linguistics, COLING

JF - Proceedings - International Conference on Computational Linguistics, COLING

IS - 1

Y2 - 12 October 2022 through 17 October 2022

ER -

GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction

Abstract

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this