@inproceedings{hemanthage-etal-2024-divide,
title = "Divide and Conquer: Rethinking Ambiguous Candidate Identification in Multimodal Dialogues with Pseudo-Labelling",
author = "Hemanthage, Bhathiya and
Dondrup, Christian and
Bilen, Hakan and
Lemon, Oliver",
editor = "Kawahara, Tatsuya and
Demberg, Vera and
Ultes, Stefan and
Inoue, Koji and
Mehri, Shikib and
Howcroft, David and
Komatani, Kazunori",
booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigdial-1.20",
pages = "222--227",
abstract = "Ambiguous Candidate Identification(ACI) in multimodal dialogue is the task of identifying all potential objects that a user{'}s utterance could be referring to in a visual scene, in cases where the reference cannot be uniquely determined. End-to-end models are the dominant approach for this task, but have limited real-world applicability due to unrealistic inference-time assumptions such as requiring predefined catalogues of items. Focusing on a more generalized and realistic ACI setup, we demonstrate that a modular approach, which first emphasizes language-only reasoning over dialogue context before performing vision-language fusion, significantly outperforms end-to-end trained baselines. To mitigate the lack of annotations for training the language-only module (student), we propose a pseudo-labelling strategy with a prompted Large Language Model (LLM) as the teacher.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hemanthage-etal-2024-divide">
<titleInfo>
<title>Divide and Conquer: Rethinking Ambiguous Candidate Identification in Multimodal Dialogues with Pseudo-Labelling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bhathiya</namePart>
<namePart type="family">Hemanthage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Dondrup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hakan</namePart>
<namePart type="family">Bilen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Lemon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikib</namePart>
<namePart type="family">Mehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Howcroft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyoto, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ambiguous Candidate Identification(ACI) in multimodal dialogue is the task of identifying all potential objects that a user’s utterance could be referring to in a visual scene, in cases where the reference cannot be uniquely determined. End-to-end models are the dominant approach for this task, but have limited real-world applicability due to unrealistic inference-time assumptions such as requiring predefined catalogues of items. Focusing on a more generalized and realistic ACI setup, we demonstrate that a modular approach, which first emphasizes language-only reasoning over dialogue context before performing vision-language fusion, significantly outperforms end-to-end trained baselines. To mitigate the lack of annotations for training the language-only module (student), we propose a pseudo-labelling strategy with a prompted Large Language Model (LLM) as the teacher.</abstract>
<identifier type="citekey">hemanthage-etal-2024-divide</identifier>
<location>
<url>https://aclanthology.org/2024.sigdial-1.20</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>222</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Divide and Conquer: Rethinking Ambiguous Candidate Identification in Multimodal Dialogues with Pseudo-Labelling
%A Hemanthage, Bhathiya
%A Dondrup, Christian
%A Bilen, Hakan
%A Lemon, Oliver
%Y Kawahara, Tatsuya
%Y Demberg, Vera
%Y Ultes, Stefan
%Y Inoue, Koji
%Y Mehri, Shikib
%Y Howcroft, David
%Y Komatani, Kazunori
%S Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F hemanthage-etal-2024-divide
%X Ambiguous Candidate Identification(ACI) in multimodal dialogue is the task of identifying all potential objects that a user’s utterance could be referring to in a visual scene, in cases where the reference cannot be uniquely determined. End-to-end models are the dominant approach for this task, but have limited real-world applicability due to unrealistic inference-time assumptions such as requiring predefined catalogues of items. Focusing on a more generalized and realistic ACI setup, we demonstrate that a modular approach, which first emphasizes language-only reasoning over dialogue context before performing vision-language fusion, significantly outperforms end-to-end trained baselines. To mitigate the lack of annotations for training the language-only module (student), we propose a pseudo-labelling strategy with a prompted Large Language Model (LLM) as the teacher.
%U https://aclanthology.org/2024.sigdial-1.20
%P 222-227
Markdown (Informal)
[Divide and Conquer: Rethinking Ambiguous Candidate Identification in Multimodal Dialogues with Pseudo-Labelling](https://aclanthology.org/2024.sigdial-1.20) (Hemanthage et al., SIGDIAL 2024)
ACL