@inproceedings{takmaz-etal-2023-speaking,
title = "Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind",
author = "Takmaz, Ece and
Brandizzi, Nicolo{'} and
Giulianelli, Mario and
Pezzelle, Sandro and
Fernandez, Raquel",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.258",
doi = "10.18653/v1/2023.findings-acl.258",
pages = "4198--4217",
abstract = "Dialogue participants may have varying levels of knowledge about the topic under discussion. In such cases, it is essential for speakers to adapt their utterances by taking their audience into account. Yet, it is an open question how such adaptation can be modelled in computational agents. In this paper, we model a visually grounded referential game between a knowledgeable speaker and a listener with more limited visual and linguistic experience. Inspired by psycholinguistic theories, we endow our speaker with the ability to adapt its referring expressions via a simulation module that monitors the effectiveness of planned utterances from the listener{'}s perspective. We propose an adaptation mechanism building on plug-and-play approaches to controlled language generation, where utterance generation is steered on the fly by the simulator without finetuning the speaker{'}s underlying language model. Our results and analyses show that our approach is effective: the speaker{'}s utterances become closer to the listener{'}s domain of expertise, which leads to higher communicative success.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takmaz-etal-2023-speaking">
<titleInfo>
<title>Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolo’</namePart>
<namePart type="family">Brandizzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Giulianelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandro</namePart>
<namePart type="family">Pezzelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernandez</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Dialogue participants may have varying levels of knowledge about the topic under discussion. In such cases, it is essential for speakers to adapt their utterances by taking their audience into account. Yet, it is an open question how such adaptation can be modelled in computational agents. In this paper, we model a visually grounded referential game between a knowledgeable speaker and a listener with more limited visual and linguistic experience. Inspired by psycholinguistic theories, we endow our speaker with the ability to adapt its referring expressions via a simulation module that monitors the effectiveness of planned utterances from the listener’s perspective. We propose an adaptation mechanism building on plug-and-play approaches to controlled language generation, where utterance generation is steered on the fly by the simulator without finetuning the speaker’s underlying language model. Our results and analyses show that our approach is effective: the speaker’s utterances become closer to the listener’s domain of expertise, which leads to higher communicative success.</abstract>
<identifier type="citekey">takmaz-etal-2023-speaking</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.258</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.258</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>4198</start>
<end>4217</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind
%A Takmaz, Ece
%A Brandizzi, Nicolo’
%A Giulianelli, Mario
%A Pezzelle, Sandro
%A Fernandez, Raquel
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F takmaz-etal-2023-speaking
%X Dialogue participants may have varying levels of knowledge about the topic under discussion. In such cases, it is essential for speakers to adapt their utterances by taking their audience into account. Yet, it is an open question how such adaptation can be modelled in computational agents. In this paper, we model a visually grounded referential game between a knowledgeable speaker and a listener with more limited visual and linguistic experience. Inspired by psycholinguistic theories, we endow our speaker with the ability to adapt its referring expressions via a simulation module that monitors the effectiveness of planned utterances from the listener’s perspective. We propose an adaptation mechanism building on plug-and-play approaches to controlled language generation, where utterance generation is steered on the fly by the simulator without finetuning the speaker’s underlying language model. Our results and analyses show that our approach is effective: the speaker’s utterances become closer to the listener’s domain of expertise, which leads to higher communicative success.
%R 10.18653/v1/2023.findings-acl.258
%U https://aclanthology.org/2023.findings-acl.258
%U https://doi.org/10.18653/v1/2023.findings-acl.258
%P 4198-4217
Markdown (Informal)
[Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind](https://aclanthology.org/2023.findings-acl.258) (Takmaz et al., Findings 2023)
ACL