@inproceedings{roman-roman-etal-2020-rmm,
title = "{RMM}: A Recursive Mental Model for Dialogue Navigation",
author = "Roman Roman, Homero and
Bisk, Yonatan and
Thomason, Jesse and
Celikyilmaz, Asli and
Gao, Jianfeng",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.157/",
doi = "10.18653/v1/2020.findings-emnlp.157",
pages = "1732--1745",
abstract = "Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers. Inspired by theory of mind, we propose the Recursive Mental Model (RMM). The navigating agent models the guiding agent to simulate answers given candidate generated questions. The guiding agent in turn models the navigating agent to simulate navigation steps it would take to generate answers. We use the progress agents make towards the goal as a reinforcement learning reward signal to directly inform not only navigation actions, but also both question and answer generation. We demonstrate that RMM enables better generalization to novel environments. Interlocutor modelling may be a way forward for human-agent RMM where robots need to both ask and answer questions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roman-roman-etal-2020-rmm">
<titleInfo>
<title>RMM: A Recursive Mental Model for Dialogue Navigation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Homero</namePart>
<namePart type="family">Roman Roman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Bisk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Thomason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers. Inspired by theory of mind, we propose the Recursive Mental Model (RMM). The navigating agent models the guiding agent to simulate answers given candidate generated questions. The guiding agent in turn models the navigating agent to simulate navigation steps it would take to generate answers. We use the progress agents make towards the goal as a reinforcement learning reward signal to directly inform not only navigation actions, but also both question and answer generation. We demonstrate that RMM enables better generalization to novel environments. Interlocutor modelling may be a way forward for human-agent RMM where robots need to both ask and answer questions.</abstract>
<identifier type="citekey">roman-roman-etal-2020-rmm</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.157</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.157/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1732</start>
<end>1745</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RMM: A Recursive Mental Model for Dialogue Navigation
%A Roman Roman, Homero
%A Bisk, Yonatan
%A Thomason, Jesse
%A Celikyilmaz, Asli
%A Gao, Jianfeng
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F roman-roman-etal-2020-rmm
%X Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers. Inspired by theory of mind, we propose the Recursive Mental Model (RMM). The navigating agent models the guiding agent to simulate answers given candidate generated questions. The guiding agent in turn models the navigating agent to simulate navigation steps it would take to generate answers. We use the progress agents make towards the goal as a reinforcement learning reward signal to directly inform not only navigation actions, but also both question and answer generation. We demonstrate that RMM enables better generalization to novel environments. Interlocutor modelling may be a way forward for human-agent RMM where robots need to both ask and answer questions.
%R 10.18653/v1/2020.findings-emnlp.157
%U https://aclanthology.org/2020.findings-emnlp.157/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.157
%P 1732-1745
Markdown (Informal)
[RMM: A Recursive Mental Model for Dialogue Navigation](https://aclanthology.org/2020.findings-emnlp.157/) (Roman Roman et al., Findings 2020)
ACL
- Homero Roman Roman, Yonatan Bisk, Jesse Thomason, Asli Celikyilmaz, and Jianfeng Gao. 2020. RMM: A Recursive Mental Model for Dialogue Navigation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1732–1745, Online. Association for Computational Linguistics.