A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication

Maryam Zare; Alan R. Wagner; Rebecca Jane Passonneau

doi:10.18653/v1/2022.findings-emnlp.513

A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication

Maryam Zare, Alan R. Wagner, Rebecca Jane Passonneau

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

Abstract

Agents to assist with rescue, surgery, and similar activities could collaborate better with humans if they could learn new strategic behaviors through communication. We introduce a novel POMDP dialogue policy for learning from people. The policy has 3-way grounding of language in the shared physical context, the dialogue context, and persistent knowledge. It can learn distinct but related games, and can continue learning across dialogues for complex games. A novel sensing component supports adaptation to information-sharing differences across people. The single policy performs better than oracle policies customized to specific games and information behavior.

Original language	English (US)
Title of host publication	Findings of the Association for Computational Linguistics
Subtitle of host publication	EMNLP 2022
Editors	Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Publisher	Association for Computational Linguistics (ACL)
Pages	6796-6809
Number of pages	14
ISBN (Electronic)	9781959429432
DOIs	https://doi.org/10.18653/v1/2022.findings-emnlp.513
State	Published - 2022
Event	2022 Findings of the Association for Computational Linguistics: EMNLP 2022 - Hybrid, Abu Dhabi, United Arab Emirates Duration: Dec 7 2022 → Dec 11 2022

Publication series

Name	Findings of the Association for Computational Linguistics: EMNLP 2022

Conference

Conference	2022 Findings of the Association for Computational Linguistics: EMNLP 2022
Country/Territory	United Arab Emirates
City	Hybrid, Abu Dhabi
Period	12/7/22 → 12/11/22

All Science Journal Classification (ASJC) codes

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Access to Document

10.18653/v1/2022.findings-emnlp.513

Cite this

Zare, M., Wagner, A. R., & Passonneau, R. J. (2022). A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication. In Y. Goldberg, Z. Kozareva, & Y. Zhang (Eds.), Findings of the Association for Computational Linguistics: EMNLP 2022 (pp. 6796-6809). (Findings of the Association for Computational Linguistics: EMNLP 2022). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.findings-emnlp.513

Zare, Maryam ; Wagner, Alan R. ; Passonneau, Rebecca Jane. / A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication. Findings of the Association for Computational Linguistics: EMNLP 2022. editor / Yoav Goldberg ; Zornitsa Kozareva ; Yue Zhang. Association for Computational Linguistics (ACL), 2022. pp. 6796-6809 (Findings of the Association for Computational Linguistics: EMNLP 2022).

@inproceedings{889e1df208cd448dbf929028e888d0ac,

title = "A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication",

abstract = "Agents to assist with rescue, surgery, and similar activities could collaborate better with humans if they could learn new strategic behaviors through communication. We introduce a novel POMDP dialogue policy for learning from people. The policy has 3-way grounding of language in the shared physical context, the dialogue context, and persistent knowledge. It can learn distinct but related games, and can continue learning across dialogues for complex games. A novel sensing component supports adaptation to information-sharing differences across people. The single policy performs better than oracle policies customized to specific games and information behavior.",

author = "Maryam Zare and Wagner, {Alan R.} and Passonneau, {Rebecca Jane}",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 2022 Findings of the Association for Computational Linguistics: EMNLP 2022 ; Conference date: 07-12-2022 Through 11-12-2022",

year = "2022",

doi = "10.18653/v1/2022.findings-emnlp.513",

language = "English (US)",

series = "Findings of the Association for Computational Linguistics: EMNLP 2022",

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

pages = "6796--6809",

editor = "Yoav Goldberg and Zornitsa Kozareva and Yue Zhang",

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

}

Zare, M, Wagner, AR & Passonneau, RJ 2022, A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication. in Y Goldberg, Z Kozareva & Y Zhang (eds), Findings of the Association for Computational Linguistics: EMNLP 2022. Findings of the Association for Computational Linguistics: EMNLP 2022, Association for Computational Linguistics (ACL), pp. 6796-6809, 2022 Findings of the Association for Computational Linguistics: EMNLP 2022, Hybrid, Abu Dhabi, United Arab Emirates, 12/7/22. https://doi.org/10.18653/v1/2022.findings-emnlp.513

A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication. / Zare, Maryam; Wagner, Alan R.; Passonneau, Rebecca Jane.
Findings of the Association for Computational Linguistics: EMNLP 2022. ed. / Yoav Goldberg; Zornitsa Kozareva; Yue Zhang. Association for Computational Linguistics (ACL), 2022. p. 6796-6809 (Findings of the Association for Computational Linguistics: EMNLP 2022).

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

TY - GEN

T1 - A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication

AU - Zare, Maryam

AU - Wagner, Alan R.

AU - Passonneau, Rebecca Jane

PY - 2022

Y1 - 2022

N2 - Agents to assist with rescue, surgery, and similar activities could collaborate better with humans if they could learn new strategic behaviors through communication. We introduce a novel POMDP dialogue policy for learning from people. The policy has 3-way grounding of language in the shared physical context, the dialogue context, and persistent knowledge. It can learn distinct but related games, and can continue learning across dialogues for complex games. A novel sensing component supports adaptation to information-sharing differences across people. The single policy performs better than oracle policies customized to specific games and information behavior.

AB - Agents to assist with rescue, surgery, and similar activities could collaborate better with humans if they could learn new strategic behaviors through communication. We introduce a novel POMDP dialogue policy for learning from people. The policy has 3-way grounding of language in the shared physical context, the dialogue context, and persistent knowledge. It can learn distinct but related games, and can continue learning across dialogues for complex games. A novel sensing component supports adaptation to information-sharing differences across people. The single policy performs better than oracle policies customized to specific games and information behavior.

UR - http://www.scopus.com/inward/record.url?scp=85149825074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85149825074&partnerID=8YFLogxK

U2 - 10.18653/v1/2022.findings-emnlp.513

DO - 10.18653/v1/2022.findings-emnlp.513

M3 - Conference contribution

AN - SCOPUS:85149825074

T3 - Findings of the Association for Computational Linguistics: EMNLP 2022

SP - 6796

EP - 6809

BT - Findings of the Association for Computational Linguistics

A2 - Goldberg, Yoav

A2 - Kozareva, Zornitsa

A2 - Zhang, Yue

PB - Association for Computational Linguistics (ACL)

T2 - 2022 Findings of the Association for Computational Linguistics: EMNLP 2022

Y2 - 7 December 2022 through 11 December 2022

ER -

Zare M, Wagner AR , Passonneau RJ. A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication. In Goldberg Y, Kozareva Z, Zhang Y, editors, Findings of the Association for Computational Linguistics: EMNLP 2022. Association for Computational Linguistics (ACL). 2022. p. 6796-6809. (Findings of the Association for Computational Linguistics: EMNLP 2022). doi: 10.18653/v1/2022.findings-emnlp.513

A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this