Simulating Bandit Learning from User Feedback for Extractive Question Answering

Ge Gao; Eunsol Choi; Yoav Artzi

doi:10.18653/v1/2022.acl-long.355

Simulating Bandit Learning from User Feedback for Extractive Question Answering

Ge Gao, Eunsol Choi, Yoav Artzi

Computer Science

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

Abstract

We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning scenarios with focus on reducing data annotation. We show that systems initially trained on a small number of examples can dramatically improve given feedback from users on model-predicted answers, and that one can use existing datasets to deploy systems in new domains without any annotation, but instead improving the system on-the-fly via user feedback.

Original language	English (US)
Title of host publication	ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Editors	Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Publisher	Association for Computational Linguistics (ACL)
Pages	5167-5179
Number of pages	13
ISBN (Electronic)	9781955917216
DOIs	https://doi.org/10.18653/v1/2022.acl-long.355
State	Published - 2022
Event	60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 - Dublin, Ireland Duration: May 22 2022 → May 27 2022

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
Volume	1
ISSN (Print)	0736-587X

Conference

Conference	60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
Country/Territory	Ireland
City	Dublin
Period	5/22/22 → 5/27/22

ASJC Scopus subject areas

Computer Science Applications
Linguistics and Language
Language and Linguistics

Access to Document

10.18653/v1/2022.acl-long.355

Cite this

Gao, G., Choi, E., & Artzi, Y. (2022). Simulating Bandit Learning from User Feedback for Extractive Question Answering. In S. Muresan, P. Nakov, & A. Villavicencio (Eds.), ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (pp. 5167-5179). (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 1). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.acl-long.355

Simulating Bandit Learning from User Feedback for Extractive Question Answering. / Gao, Ge; Choi, Eunsol; Artzi, Yoav.
ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). ed. / Smaranda Muresan; Preslav Nakov; Aline Villavicencio. Association for Computational Linguistics (ACL), 2022. p. 5167-5179 (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 1).

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

Gao, G, Choi, E & Artzi, Y 2022, Simulating Bandit Learning from User Feedback for Extractive Question Answering. in S Muresan, P Nakov & A Villavicencio (eds), ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Proceedings of the Annual Meeting of the Association for Computational Linguistics, vol. 1, Association for Computational Linguistics (ACL), pp. 5167-5179, 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022, Dublin, Ireland, 5/22/22. https://doi.org/10.18653/v1/2022.acl-long.355

Gao G, Choi E, Artzi Y. Simulating Bandit Learning from User Feedback for Extractive Question Answering. In Muresan S, Nakov P, Villavicencio A, editors, ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL). 2022. p. 5167-5179. (Proceedings of the Annual Meeting of the Association for Computational Linguistics). doi: 10.18653/v1/2022.acl-long.355

Gao, Ge ; Choi, Eunsol ; Artzi, Yoav. / Simulating Bandit Learning from User Feedback for Extractive Question Answering. ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). editor / Smaranda Muresan ; Preslav Nakov ; Aline Villavicencio. Association for Computational Linguistics (ACL), 2022. pp. 5167-5179 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{5b1a6c67b9a34056a0bae28db826f2cc,

title = "Simulating Bandit Learning from User Feedback for Extractive Question Answering",

abstract = "We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning scenarios with focus on reducing data annotation. We show that systems initially trained on a small number of examples can dramatically improve given feedback from users on model-predicted answers, and that one can use existing datasets to deploy systems in new domains without any annotation, but instead improving the system on-the-fly via user feedback.",

author = "Ge Gao and Eunsol Choi and Yoav Artzi",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 ; Conference date: 22-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.18653/v1/2022.acl-long.355",

language = "English (US)",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

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

pages = "5167--5179",

editor = "Smaranda Muresan and Preslav Nakov and Aline Villavicencio",

booktitle = "ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

}

TY - GEN

T1 - Simulating Bandit Learning from User Feedback for Extractive Question Answering

AU - Gao, Ge

AU - Choi, Eunsol

AU - Artzi, Yoav

PY - 2022

Y1 - 2022

N2 - We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning scenarios with focus on reducing data annotation. We show that systems initially trained on a small number of examples can dramatically improve given feedback from users on model-predicted answers, and that one can use existing datasets to deploy systems in new domains without any annotation, but instead improving the system on-the-fly via user feedback.

AB - We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning scenarios with focus on reducing data annotation. We show that systems initially trained on a small number of examples can dramatically improve given feedback from users on model-predicted answers, and that one can use existing datasets to deploy systems in new domains without any annotation, but instead improving the system on-the-fly via user feedback.

UR - http://www.scopus.com/inward/record.url?scp=85144946591&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85144946591&partnerID=8YFLogxK

U2 - 10.18653/v1/2022.acl-long.355

DO - 10.18653/v1/2022.acl-long.355

M3 - Conference contribution

AN - SCOPUS:85144946591

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 5167

EP - 5179

BT - ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

A2 - Muresan, Smaranda

A2 - Nakov, Preslav

A2 - Villavicencio, Aline

PB - Association for Computational Linguistics (ACL)

T2 - 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022

Y2 - 22 May 2022 through 27 May 2022

ER -

Simulating Bandit Learning from User Feedback for Extractive Question Answering

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this