Incorporating Task-Specific Concept Knowledge into Script Learning

Chenkai Sun; Tie Xu; Cheng Xiang Zhai; Heng Ji

Incorporating Task-Specific Concept Knowledge into Script Learning

Chenkai Sun, Tie Xu, Cheng Xiang Zhai, Heng Ji

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

Abstract

In this paper, we present TETRIS, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance.

Original language	English (US)
Title of host publication	EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	3018-3032
Number of pages	15
ISBN (Electronic)	9781959429449
State	Published - 2023
Event	17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Dubrovnik, Croatia Duration: May 2 2023 → May 6 2023

Publication series

Name	EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference	17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023
Country/Territory	Croatia
City	Dubrovnik
Period	5/2/23 → 5/6/23

ASJC Scopus subject areas

Computational Theory and Mathematics
Software
Linguistics and Language

Library availability

Discover UIUC Full Text

Cite this

Sun, C., Xu, T., Zhai, C. X., & Ji, H. (2023). Incorporating Task-Specific Concept Knowledge into Script Learning. In EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 3018-3032). (EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

Incorporating Task-Specific Concept Knowledge into Script Learning. / Sun, Chenkai; Xu, Tie; Zhai, Cheng Xiang et al.
EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2023. p. 3018-3032 (EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference).

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

Sun, C, Xu, T, Zhai, CX & Ji, H 2023, Incorporating Task-Specific Concept Knowledge into Script Learning. in EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 3018-3032, 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023, Dubrovnik, Croatia, 5/2/23.

Sun C, Xu T, Zhai CX , Ji H. Incorporating Task-Specific Concept Knowledge into Script Learning. In EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2023. p. 3018-3032. (EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference).

Sun, Chenkai ; Xu, Tie ; Zhai, Cheng Xiang et al. / Incorporating Task-Specific Concept Knowledge into Script Learning. EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2023. pp. 3018-3032 (EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference).

@inproceedings{82d2d748316a4519a7c080b460f8a782,

title = "Incorporating Task-Specific Concept Knowledge into Script Learning",

abstract = "In this paper, we present TETRIS, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance.",

author = "Chenkai Sun and Tie Xu and Zhai, {Cheng Xiang} and Heng Ji",

note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 ; Conference date: 02-05-2023 Through 06-05-2023",

year = "2023",

language = "English (US)",

series = "EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference",

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

pages = "3018--3032",

booktitle = "EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - Incorporating Task-Specific Concept Knowledge into Script Learning

AU - Sun, Chenkai

AU - Xu, Tie

AU - Zhai, Cheng Xiang

AU - Ji, Heng

PY - 2023

Y1 - 2023

N2 - In this paper, we present TETRIS, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance.

AB - In this paper, we present TETRIS, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance.

UR - http://www.scopus.com/inward/record.url?scp=85159861790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85159861790&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85159861790

T3 - EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

SP - 3018

EP - 3032

BT - EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023

Y2 - 2 May 2023 through 6 May 2023

ER -

Incorporating Task-Specific Concept Knowledge into Script Learning

Abstract

Publication series

Conference

ASJC Scopus subject areas

Library availability

Related links

Fingerprint

Cite this