@inproceedings{fried-etal-2021-reference,
title = "Reference-Centric Models for Grounded Collaborative Dialogue",
author = "Fried, Daniel and
Chiu, Justin and
Klein, Dan",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.163",
doi = "10.18653/v1/2021.emnlp-main.163",
pages = "2130--2147",
abstract = "We present a grounded neural dialogue model that successfully collaborates with people in a partially-observable reference game. We focus on a setting where two agents each observe an overlapping part of a world context and need to identify and agree on some object they share. Therefore, the agents should pool their information and communicate pragmatically to solve the task. Our dialogue agent accurately grounds referents from the partner{'}s utterances using a structured reference resolver, conditions on these referents using a recurrent memory, and uses a pragmatic generation procedure to ensure the partner can resolve the references the agent produces. We evaluate on the OneCommon spatial grounding dialogue task (Udagawa and Aizawa 2019), involving a number of dots arranged on a board with continuously varying positions, sizes, and shades. Our agent substantially outperforms the previous state of the art for the task, obtaining a 20{\%} relative improvement in successful task completion in self-play evaluations and a 50{\%} relative improvement in success in human evaluations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fried-etal-2021-reference">
<titleInfo>
<title>Reference-Centric Models for Grounded Collaborative Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Fried</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Chiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a grounded neural dialogue model that successfully collaborates with people in a partially-observable reference game. We focus on a setting where two agents each observe an overlapping part of a world context and need to identify and agree on some object they share. Therefore, the agents should pool their information and communicate pragmatically to solve the task. Our dialogue agent accurately grounds referents from the partner’s utterances using a structured reference resolver, conditions on these referents using a recurrent memory, and uses a pragmatic generation procedure to ensure the partner can resolve the references the agent produces. We evaluate on the OneCommon spatial grounding dialogue task (Udagawa and Aizawa 2019), involving a number of dots arranged on a board with continuously varying positions, sizes, and shades. Our agent substantially outperforms the previous state of the art for the task, obtaining a 20% relative improvement in successful task completion in self-play evaluations and a 50% relative improvement in success in human evaluations.</abstract>
<identifier type="citekey">fried-etal-2021-reference</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.163</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.163</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2130</start>
<end>2147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reference-Centric Models for Grounded Collaborative Dialogue
%A Fried, Daniel
%A Chiu, Justin
%A Klein, Dan
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F fried-etal-2021-reference
%X We present a grounded neural dialogue model that successfully collaborates with people in a partially-observable reference game. We focus on a setting where two agents each observe an overlapping part of a world context and need to identify and agree on some object they share. Therefore, the agents should pool their information and communicate pragmatically to solve the task. Our dialogue agent accurately grounds referents from the partner’s utterances using a structured reference resolver, conditions on these referents using a recurrent memory, and uses a pragmatic generation procedure to ensure the partner can resolve the references the agent produces. We evaluate on the OneCommon spatial grounding dialogue task (Udagawa and Aizawa 2019), involving a number of dots arranged on a board with continuously varying positions, sizes, and shades. Our agent substantially outperforms the previous state of the art for the task, obtaining a 20% relative improvement in successful task completion in self-play evaluations and a 50% relative improvement in success in human evaluations.
%R 10.18653/v1/2021.emnlp-main.163
%U https://aclanthology.org/2021.emnlp-main.163
%U https://doi.org/10.18653/v1/2021.emnlp-main.163
%P 2130-2147
Markdown (Informal)
[Reference-Centric Models for Grounded Collaborative Dialogue](https://aclanthology.org/2021.emnlp-main.163) (Fried et al., EMNLP 2021)
ACL
- Daniel Fried, Justin Chiu, and Dan Klein. 2021. Reference-Centric Models for Grounded Collaborative Dialogue. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2130–2147, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.