@inproceedings{krishnaswamy-pustejovsky-2019-generating,
title = "Generating a Novel Dataset of Multimodal Referring Expressions",
author = "Krishnaswamy, Nikhil and
Pustejovsky, James",
editor = "Dobnik, Simon and
Chatzikyriakidis, Stergios and
Demberg, Vera",
booktitle = "Proceedings of the 13th International Conference on Computational Semantics - Short Papers",
month = may,
year = "2019",
address = "Gothenburg, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-0507",
doi = "10.18653/v1/W19-0507",
pages = "44--51",
abstract = "Referring expressions and definite descriptions of objects in space exploit information both about object characteristics and locations. To resolve potential ambiguity, referencing strategies in language can rely on increasingly abstract concepts to distinguish an object in a given location from similar ones elsewhere, yet the description of the intended location may still be imprecise or difficult to interpret. Meanwhile, modalities such as gesture may communicate spatial information such as locations in a more concise manner. In real peer-to-peer communication, humans use language and gesture together to reference entities, with a capacity for mixing and changing modalities where needed. While recent progress in AI and human-computer interaction has created systems where a human can interact with a computer multimodally, computers often lack the capacity to intelligently mix modalities when generating referring expressions. We present a novel dataset of referring expressions combining natural language and gesture, describe its creation and evaluation, and its uses to train computational models for generating and interpreting multimodal referring expressions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishnaswamy-pustejovsky-2019-generating">
<titleInfo>
<title>Generating a Novel Dataset of Multimodal Referring Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Krishnaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Conference on Computational Semantics - Short Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stergios</namePart>
<namePart type="family">Chatzikyriakidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gothenburg, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Referring expressions and definite descriptions of objects in space exploit information both about object characteristics and locations. To resolve potential ambiguity, referencing strategies in language can rely on increasingly abstract concepts to distinguish an object in a given location from similar ones elsewhere, yet the description of the intended location may still be imprecise or difficult to interpret. Meanwhile, modalities such as gesture may communicate spatial information such as locations in a more concise manner. In real peer-to-peer communication, humans use language and gesture together to reference entities, with a capacity for mixing and changing modalities where needed. While recent progress in AI and human-computer interaction has created systems where a human can interact with a computer multimodally, computers often lack the capacity to intelligently mix modalities when generating referring expressions. We present a novel dataset of referring expressions combining natural language and gesture, describe its creation and evaluation, and its uses to train computational models for generating and interpreting multimodal referring expressions.</abstract>
<identifier type="citekey">krishnaswamy-pustejovsky-2019-generating</identifier>
<identifier type="doi">10.18653/v1/W19-0507</identifier>
<location>
<url>https://aclanthology.org/W19-0507</url>
</location>
<part>
<date>2019-05</date>
<extent unit="page">
<start>44</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating a Novel Dataset of Multimodal Referring Expressions
%A Krishnaswamy, Nikhil
%A Pustejovsky, James
%Y Dobnik, Simon
%Y Chatzikyriakidis, Stergios
%Y Demberg, Vera
%S Proceedings of the 13th International Conference on Computational Semantics - Short Papers
%D 2019
%8 May
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F krishnaswamy-pustejovsky-2019-generating
%X Referring expressions and definite descriptions of objects in space exploit information both about object characteristics and locations. To resolve potential ambiguity, referencing strategies in language can rely on increasingly abstract concepts to distinguish an object in a given location from similar ones elsewhere, yet the description of the intended location may still be imprecise or difficult to interpret. Meanwhile, modalities such as gesture may communicate spatial information such as locations in a more concise manner. In real peer-to-peer communication, humans use language and gesture together to reference entities, with a capacity for mixing and changing modalities where needed. While recent progress in AI and human-computer interaction has created systems where a human can interact with a computer multimodally, computers often lack the capacity to intelligently mix modalities when generating referring expressions. We present a novel dataset of referring expressions combining natural language and gesture, describe its creation and evaluation, and its uses to train computational models for generating and interpreting multimodal referring expressions.
%R 10.18653/v1/W19-0507
%U https://aclanthology.org/W19-0507
%U https://doi.org/10.18653/v1/W19-0507
%P 44-51
Markdown (Informal)
[Generating a Novel Dataset of Multimodal Referring Expressions](https://aclanthology.org/W19-0507) (Krishnaswamy & Pustejovsky, IWCS 2019)
ACL