@inproceedings{rubavicius-lascarides-2022-interactive,
title = "Interactive Symbol Grounding with Complex Referential Expressions",
author = "Rubavicius, Rimvydas and
Lascarides, Alex",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.358",
doi = "10.18653/v1/2022.naacl-main.358",
pages = "4863--4874",
abstract = "We present a procedure for learning to ground symbols from a sequence of stimuli consisting of an arbitrarily complex noun phrase (e.g. {``}all but one green square above both red circles.{''}) and its designation in the visual scene. Our distinctive approach combines: a) lazy few-shot learning to relate open-class words like green and above to their visual percepts; and b) symbolic reasoning with closed-class word categories like quantifiers and negation. We use this combination to estimate new training examples for grounding symbols that occur \textit{within} a noun phrase but aren{'}t designated by that noun phase (e.g, red in the above example), thereby potentially gaining data efficiency. We evaluate the approach in a visual reference resolution task, in which the learner starts out unaware of concepts that are part of the domain model and how they relate to visual percepts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rubavicius-lascarides-2022-interactive">
<titleInfo>
<title>Interactive Symbol Grounding with Complex Referential Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rimvydas</namePart>
<namePart type="family">Rubavicius</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>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a procedure for learning to ground symbols from a sequence of stimuli consisting of an arbitrarily complex noun phrase (e.g. “all but one green square above both red circles.”) and its designation in the visual scene. Our distinctive approach combines: a) lazy few-shot learning to relate open-class words like green and above to their visual percepts; and b) symbolic reasoning with closed-class word categories like quantifiers and negation. We use this combination to estimate new training examples for grounding symbols that occur within a noun phrase but aren’t designated by that noun phase (e.g, red in the above example), thereby potentially gaining data efficiency. We evaluate the approach in a visual reference resolution task, in which the learner starts out unaware of concepts that are part of the domain model and how they relate to visual percepts.</abstract>
<identifier type="citekey">rubavicius-lascarides-2022-interactive</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.358</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.358</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>4863</start>
<end>4874</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interactive Symbol Grounding with Complex Referential Expressions
%A Rubavicius, Rimvydas
%A Lascarides, Alex
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F rubavicius-lascarides-2022-interactive
%X We present a procedure for learning to ground symbols from a sequence of stimuli consisting of an arbitrarily complex noun phrase (e.g. “all but one green square above both red circles.”) and its designation in the visual scene. Our distinctive approach combines: a) lazy few-shot learning to relate open-class words like green and above to their visual percepts; and b) symbolic reasoning with closed-class word categories like quantifiers and negation. We use this combination to estimate new training examples for grounding symbols that occur within a noun phrase but aren’t designated by that noun phase (e.g, red in the above example), thereby potentially gaining data efficiency. We evaluate the approach in a visual reference resolution task, in which the learner starts out unaware of concepts that are part of the domain model and how they relate to visual percepts.
%R 10.18653/v1/2022.naacl-main.358
%U https://aclanthology.org/2022.naacl-main.358
%U https://doi.org/10.18653/v1/2022.naacl-main.358
%P 4863-4874
Markdown (Informal)
[Interactive Symbol Grounding with Complex Referential Expressions](https://aclanthology.org/2022.naacl-main.358) (Rubavicius & Lascarides, NAACL 2022)
ACL
- Rimvydas Rubavicius and Alex Lascarides. 2022. Interactive Symbol Grounding with Complex Referential Expressions. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4863–4874, Seattle, United States. Association for Computational Linguistics.