@inproceedings{park-etal-2023-interactive,
title = "Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse",
author = "Park, Jonghyuk and
Lascarides, Alex and
Ramamoorthy, Subramanian",
editor = "Amblard, Maxime and
Breitholtz, Ellen",
booktitle = "Proceedings of the 15th International Conference on Computational Semantics",
month = jun,
year = "2023",
address = "Nancy, France",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwcs-1.33",
pages = "318--331",
abstract = "Interactive Task Learning (ITL) concerns learning about unforeseen domain concepts via natural interactions with human users. The learner faces a number of significant constraints: learning should be online, incremental and few-shot, as it is expected to perform tangible belief updates right after novel words denoting unforeseen concepts are introduced. In this work, we explore a challenging symbol grounding task{---}discriminating among object classes that look very similar{---}within the constraints imposed by ITL. We demonstrate empirically that more data-efficient grounding results from exploiting the truth-conditions of the teacher{'}s generic statements (e.g., {``}Xs have attribute Z.{''}) and their implicatures in context (e.g., as an answer to {``}How are Xs and Ys different?{''}, one infers Y lacks attribute Z).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2023-interactive">
<titleInfo>
<title>Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonghyuk</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Lascarides</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subramanian</namePart>
<namePart type="family">Ramamoorthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Computational Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maxime</namePart>
<namePart type="family">Amblard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Breitholtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Nancy, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Interactive Task Learning (ITL) concerns learning about unforeseen domain concepts via natural interactions with human users. The learner faces a number of significant constraints: learning should be online, incremental and few-shot, as it is expected to perform tangible belief updates right after novel words denoting unforeseen concepts are introduced. In this work, we explore a challenging symbol grounding task—discriminating among object classes that look very similar—within the constraints imposed by ITL. We demonstrate empirically that more data-efficient grounding results from exploiting the truth-conditions of the teacher’s generic statements (e.g., “Xs have attribute Z.”) and their implicatures in context (e.g., as an answer to “How are Xs and Ys different?”, one infers Y lacks attribute Z).</abstract>
<identifier type="citekey">park-etal-2023-interactive</identifier>
<location>
<url>https://aclanthology.org/2023.iwcs-1.33</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>318</start>
<end>331</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse
%A Park, Jonghyuk
%A Lascarides, Alex
%A Ramamoorthy, Subramanian
%Y Amblard, Maxime
%Y Breitholtz, Ellen
%S Proceedings of the 15th International Conference on Computational Semantics
%D 2023
%8 June
%I Association for Computational Linguistics
%C Nancy, France
%F park-etal-2023-interactive
%X Interactive Task Learning (ITL) concerns learning about unforeseen domain concepts via natural interactions with human users. The learner faces a number of significant constraints: learning should be online, incremental and few-shot, as it is expected to perform tangible belief updates right after novel words denoting unforeseen concepts are introduced. In this work, we explore a challenging symbol grounding task—discriminating among object classes that look very similar—within the constraints imposed by ITL. We demonstrate empirically that more data-efficient grounding results from exploiting the truth-conditions of the teacher’s generic statements (e.g., “Xs have attribute Z.”) and their implicatures in context (e.g., as an answer to “How are Xs and Ys different?”, one infers Y lacks attribute Z).
%U https://aclanthology.org/2023.iwcs-1.33
%P 318-331
Markdown (Informal)
[Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse](https://aclanthology.org/2023.iwcs-1.33) (Park et al., IWCS 2023)
ACL