@inproceedings{zarriess-schlangen-2019-know,
title = "Know What You Don{'}t Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories",
author = "Zarrie{\ss}, Sina and
Schlangen, David",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1063",
doi = "10.18653/v1/P19-1063",
pages = "654--659",
abstract = "Zero-shot learning in Language {\&} Vision is the task of correctly labelling (or naming) objects of novel categories. Another strand of work in L{\&}V aims at pragmatically informative rather than {``}correct{''} object descriptions, e.g. in reference games. We combine these lines of research and model zero-shot reference games, where a speaker needs to successfully refer to a novel object in an image. Inspired by models of {``}rational speech acts{''}, we extend a neural generator to become a pragmatic speaker reasoning about uncertain object categories. As a result of this reasoning, the generator produces fewer nouns and names of distractor categories as compared to a literal speaker. We show that this conversational strategy for dealing with novel objects often improves communicative success, in terms of resolution accuracy of an automatic listener.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zarriess-schlangen-2019-know">
<titleInfo>
<title>Know What You Don’t Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</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>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Zero-shot learning in Language & Vision is the task of correctly labelling (or naming) objects of novel categories. Another strand of work in L&V aims at pragmatically informative rather than “correct” object descriptions, e.g. in reference games. We combine these lines of research and model zero-shot reference games, where a speaker needs to successfully refer to a novel object in an image. Inspired by models of “rational speech acts”, we extend a neural generator to become a pragmatic speaker reasoning about uncertain object categories. As a result of this reasoning, the generator produces fewer nouns and names of distractor categories as compared to a literal speaker. We show that this conversational strategy for dealing with novel objects often improves communicative success, in terms of resolution accuracy of an automatic listener.</abstract>
<identifier type="citekey">zarriess-schlangen-2019-know</identifier>
<identifier type="doi">10.18653/v1/P19-1063</identifier>
<location>
<url>https://aclanthology.org/P19-1063</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>654</start>
<end>659</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Know What You Don’t Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories
%A Zarrieß, Sina
%A Schlangen, David
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F zarriess-schlangen-2019-know
%X Zero-shot learning in Language & Vision is the task of correctly labelling (or naming) objects of novel categories. Another strand of work in L&V aims at pragmatically informative rather than “correct” object descriptions, e.g. in reference games. We combine these lines of research and model zero-shot reference games, where a speaker needs to successfully refer to a novel object in an image. Inspired by models of “rational speech acts”, we extend a neural generator to become a pragmatic speaker reasoning about uncertain object categories. As a result of this reasoning, the generator produces fewer nouns and names of distractor categories as compared to a literal speaker. We show that this conversational strategy for dealing with novel objects often improves communicative success, in terms of resolution accuracy of an automatic listener.
%R 10.18653/v1/P19-1063
%U https://aclanthology.org/P19-1063
%U https://doi.org/10.18653/v1/P19-1063
%P 654-659
Markdown (Informal)
[Know What You Don’t Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories](https://aclanthology.org/P19-1063) (Zarrieß & Schlangen, ACL 2019)
ACL