@inproceedings{yu-etal-2017-burchak,
title = "The {BURCHAK} corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings",
author = "Yu, Yanchao and
Eshghi, Arash and
Mills, Gregory and
Lemon, Oliver",
editor = "Belz, Anya and
Erdem, Erkut and
Pastra, Katerina and
Mikolajczyk, Krystian",
booktitle = "Proceedings of the Sixth Workshop on Vision and Language",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2001",
doi = "10.18653/v1/W17-2001",
pages = "1--10",
abstract = "We motivate and describe a new freely available human-human dialogue data set for interactive learning of visually grounded word meanings through ostensive definition by a tutor to a learner. The data has been collected using a novel, character-by-character variant of the DiET chat tool (Healey et al., 2003; anon.) with a novel task, where a Learner needs to learn invented visual attribute words (such as {``}burchak{''} for square) from a tutor. As such, the text-based interactions closely resemble face-to-face conversation and thus contain many of the linguistic phenomena encountered in natural, spontaneous dialogue. These include self- and other-correction, mid-sentence continuations, interruptions, turn overlaps, fillers, hedges and many kinds of ellipsis. We also present a generic n-gram framework for building user (i.e. tutor) simulations from this type of incremental dialogue data, which is freely available to researchers. We show that the simulations produce outputs that are similar to the original data (e.g. 78{\%} turn match similarity). Finally, we train and evaluate a Reinforcement Learning dialogue control agent for learning visually grounded word meanings, trained from the BURCHAK corpus. The learned policy shows comparable performance to a rule-based system built previously.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2017-burchak">
<titleInfo>
<title>The BURCHAK corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanchao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Eshghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gregory</namePart>
<namePart type="family">Mills</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Lemon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Vision and Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erkut</namePart>
<namePart type="family">Erdem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Pastra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krystian</namePart>
<namePart type="family">Mikolajczyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We motivate and describe a new freely available human-human dialogue data set for interactive learning of visually grounded word meanings through ostensive definition by a tutor to a learner. The data has been collected using a novel, character-by-character variant of the DiET chat tool (Healey et al., 2003; anon.) with a novel task, where a Learner needs to learn invented visual attribute words (such as “burchak” for square) from a tutor. As such, the text-based interactions closely resemble face-to-face conversation and thus contain many of the linguistic phenomena encountered in natural, spontaneous dialogue. These include self- and other-correction, mid-sentence continuations, interruptions, turn overlaps, fillers, hedges and many kinds of ellipsis. We also present a generic n-gram framework for building user (i.e. tutor) simulations from this type of incremental dialogue data, which is freely available to researchers. We show that the simulations produce outputs that are similar to the original data (e.g. 78% turn match similarity). Finally, we train and evaluate a Reinforcement Learning dialogue control agent for learning visually grounded word meanings, trained from the BURCHAK corpus. The learned policy shows comparable performance to a rule-based system built previously.</abstract>
<identifier type="citekey">yu-etal-2017-burchak</identifier>
<identifier type="doi">10.18653/v1/W17-2001</identifier>
<location>
<url>https://aclanthology.org/W17-2001</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The BURCHAK corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings
%A Yu, Yanchao
%A Eshghi, Arash
%A Mills, Gregory
%A Lemon, Oliver
%Y Belz, Anya
%Y Erdem, Erkut
%Y Pastra, Katerina
%Y Mikolajczyk, Krystian
%S Proceedings of the Sixth Workshop on Vision and Language
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F yu-etal-2017-burchak
%X We motivate and describe a new freely available human-human dialogue data set for interactive learning of visually grounded word meanings through ostensive definition by a tutor to a learner. The data has been collected using a novel, character-by-character variant of the DiET chat tool (Healey et al., 2003; anon.) with a novel task, where a Learner needs to learn invented visual attribute words (such as “burchak” for square) from a tutor. As such, the text-based interactions closely resemble face-to-face conversation and thus contain many of the linguistic phenomena encountered in natural, spontaneous dialogue. These include self- and other-correction, mid-sentence continuations, interruptions, turn overlaps, fillers, hedges and many kinds of ellipsis. We also present a generic n-gram framework for building user (i.e. tutor) simulations from this type of incremental dialogue data, which is freely available to researchers. We show that the simulations produce outputs that are similar to the original data (e.g. 78% turn match similarity). Finally, we train and evaluate a Reinforcement Learning dialogue control agent for learning visually grounded word meanings, trained from the BURCHAK corpus. The learned policy shows comparable performance to a rule-based system built previously.
%R 10.18653/v1/W17-2001
%U https://aclanthology.org/W17-2001
%U https://doi.org/10.18653/v1/W17-2001
%P 1-10
Markdown (Informal)
[The BURCHAK corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings](https://aclanthology.org/W17-2001) (Yu et al., VL 2017)
ACL