@inproceedings{madureira-schlangen-2024-taking,
title = "Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests",
author = "Madureira, Brielen and
Schlangen, David",
editor = "Pyatkin, Valentina and
Fried, Daniel and
Stengel-Eskin, Elias and
Stengel-Eskin, Elias and
Liu, Alisa and
Pezzelle, Sandro",
booktitle = "Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language",
month = mar,
year = "2024",
address = "Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.unimplicit-1.1",
pages = "1--21",
abstract = "Clarification requests are a mechanism to help solve communication problems, e.g. due to ambiguity or underspecification, in instruction-following interactions. Despite their importance, even skilful models struggle with producing or interpreting such repair acts. In this work, we test three hypotheses concerning the effects of action taking as an auxiliary task in modelling iCR policies. Contrary to initial expectations, we conclude that its contribution to learning an iCR policy is limited, but some information can still be extracted from prediction uncertainty. We present further evidence that even well-motivated, Transformer-based models fail to learn good policies for when to ask Instruction CRs (iCRs), while the task of determining what to ask about can be more successfully modelled. Considering the implications of these findings, we further discuss the shortcomings of the data-driven paradigm for learning meta-communication acts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="madureira-schlangen-2024-taking">
<titleInfo>
<title>Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brielen</namePart>
<namePart type="family">Madureira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valentina</namePart>
<namePart type="family">Pyatkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Fried</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elias</namePart>
<namePart type="family">Stengel-Eskin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alisa</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandro</namePart>
<namePart type="family">Pezzelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Clarification requests are a mechanism to help solve communication problems, e.g. due to ambiguity or underspecification, in instruction-following interactions. Despite their importance, even skilful models struggle with producing or interpreting such repair acts. In this work, we test three hypotheses concerning the effects of action taking as an auxiliary task in modelling iCR policies. Contrary to initial expectations, we conclude that its contribution to learning an iCR policy is limited, but some information can still be extracted from prediction uncertainty. We present further evidence that even well-motivated, Transformer-based models fail to learn good policies for when to ask Instruction CRs (iCRs), while the task of determining what to ask about can be more successfully modelled. Considering the implications of these findings, we further discuss the shortcomings of the data-driven paradigm for learning meta-communication acts.</abstract>
<identifier type="citekey">madureira-schlangen-2024-taking</identifier>
<location>
<url>https://aclanthology.org/2024.unimplicit-1.1</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests
%A Madureira, Brielen
%A Schlangen, David
%Y Pyatkin, Valentina
%Y Fried, Daniel
%Y Stengel-Eskin, Elias
%Y Liu, Alisa
%Y Pezzelle, Sandro
%S Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language
%D 2024
%8 March
%I Association for Computational Linguistics
%C Malta
%F madureira-schlangen-2024-taking
%X Clarification requests are a mechanism to help solve communication problems, e.g. due to ambiguity or underspecification, in instruction-following interactions. Despite their importance, even skilful models struggle with producing or interpreting such repair acts. In this work, we test three hypotheses concerning the effects of action taking as an auxiliary task in modelling iCR policies. Contrary to initial expectations, we conclude that its contribution to learning an iCR policy is limited, but some information can still be extracted from prediction uncertainty. We present further evidence that even well-motivated, Transformer-based models fail to learn good policies for when to ask Instruction CRs (iCRs), while the task of determining what to ask about can be more successfully modelled. Considering the implications of these findings, we further discuss the shortcomings of the data-driven paradigm for learning meta-communication acts.
%U https://aclanthology.org/2024.unimplicit-1.1
%P 1-21
Markdown (Informal)
[Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests](https://aclanthology.org/2024.unimplicit-1.1) (Madureira & Schlangen, unimplicit-WS 2024)
ACL