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

Maryam Zare; Alan Richard Wagner; Rebecca Jane Passonneau

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

Maryam Zare, Alan Richard Wagner, Rebecca Jane Passonneau

Research output: Contribution to conference › Paper › peer-review

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)
Pages	6796-6809
Number of pages	14
State	Published - 2022
Event	2022 Findings of the Association for Computational Linguistics: EMNLP 2022 - Abu Dhabi, United Arab Emirates Duration: Dec 7 2022 → Dec 11 2022

Conference

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

All Science Journal Classification (ASJC) codes

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Cite this

@conference{de3e09f4236d4b5f8a0c62a764232768,

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 Richard} 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",

language = "English (US)",

pages = "6796--6809",

}

A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication. / Zare, Maryam; Wagner, Alan Richard ; Passonneau, Rebecca Jane.
2022. 6796-6809 Paper presented at 2022 Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

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

AU - Zare, Maryam

AU - Wagner, Alan Richard

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

M3 - Paper

AN - SCOPUS:85149825074

SP - 6796

EP - 6809

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

Y2 - 7 December 2022 through 11 December 2022

ER -

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

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Cite this