@inproceedings{wu-etal-2023-listener,
title = "Listener Model for the {P}hoto{B}ook Referential Game with {CLIPS}cores as Implicit Reference Chain",
author = "Wu, Shih-Lun and
Chou, Yi-Hui and
Li, Liangze",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.121",
doi = "10.18653/v1/2023.acl-short.121",
pages = "1420--1432",
abstract = "PhotoBook is a collaborative dialogue game where two players receive private, partially-overlapping sets of images and resolve which images they have in common. It presents machines with a great challenge to learn how people build common ground around multimodal context to communicate effectively. Methods developed in the literature, however, cannot be deployed to real gameplaysince they only tackle some subtasks of the game,and they require additional reference chains inputs, whose extraction process is imperfect. Therefore, we propose a reference chain-free listener modelthat directly addresses the game{'}s predictive task, i.e., deciding whether an image is shared with partner. Our DeBERTa-based listener model reads the full dialogue, and utilizesCLIPScore features to assess utterance-image relevance. We achieve {\textgreater}77{\%} accuracy on unseen sets of images/game themes, outperforming baseline by {\textgreater}17 points.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2023-listener">
<titleInfo>
<title>Listener Model for the PhotoBook Referential Game with CLIPScores as Implicit Reference Chain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shih-Lun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Hui</namePart>
<namePart type="family">Chou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangze</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>PhotoBook is a collaborative dialogue game where two players receive private, partially-overlapping sets of images and resolve which images they have in common. It presents machines with a great challenge to learn how people build common ground around multimodal context to communicate effectively. Methods developed in the literature, however, cannot be deployed to real gameplaysince they only tackle some subtasks of the game,and they require additional reference chains inputs, whose extraction process is imperfect. Therefore, we propose a reference chain-free listener modelthat directly addresses the game’s predictive task, i.e., deciding whether an image is shared with partner. Our DeBERTa-based listener model reads the full dialogue, and utilizesCLIPScore features to assess utterance-image relevance. We achieve \textgreater77% accuracy on unseen sets of images/game themes, outperforming baseline by \textgreater17 points.</abstract>
<identifier type="citekey">wu-etal-2023-listener</identifier>
<identifier type="doi">10.18653/v1/2023.acl-short.121</identifier>
<location>
<url>https://aclanthology.org/2023.acl-short.121</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1420</start>
<end>1432</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Listener Model for the PhotoBook Referential Game with CLIPScores as Implicit Reference Chain
%A Wu, Shih-Lun
%A Chou, Yi-Hui
%A Li, Liangze
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wu-etal-2023-listener
%X PhotoBook is a collaborative dialogue game where two players receive private, partially-overlapping sets of images and resolve which images they have in common. It presents machines with a great challenge to learn how people build common ground around multimodal context to communicate effectively. Methods developed in the literature, however, cannot be deployed to real gameplaysince they only tackle some subtasks of the game,and they require additional reference chains inputs, whose extraction process is imperfect. Therefore, we propose a reference chain-free listener modelthat directly addresses the game’s predictive task, i.e., deciding whether an image is shared with partner. Our DeBERTa-based listener model reads the full dialogue, and utilizesCLIPScore features to assess utterance-image relevance. We achieve \textgreater77% accuracy on unseen sets of images/game themes, outperforming baseline by \textgreater17 points.
%R 10.18653/v1/2023.acl-short.121
%U https://aclanthology.org/2023.acl-short.121
%U https://doi.org/10.18653/v1/2023.acl-short.121
%P 1420-1432
Markdown (Informal)
[Listener Model for the PhotoBook Referential Game with CLIPScores as Implicit Reference Chain](https://aclanthology.org/2023.acl-short.121) (Wu et al., ACL 2023)
ACL