@inproceedings{van-miltenburg-etal-2018-didec,
title = "{DIDEC}: The {D}utch Image Description and Eye-tracking Corpus",
author = "van Miltenburg, Emiel and
K{\'a}d{\'a}r, {\'A}kos and
Koolen, Ruud and
Krahmer, Emiel",
editor = "Bender, Emily M. and
Derczynski, Leon and
Isabelle, Pierre",
booktitle = "Proceedings of the 27th International Conference on Computational Linguistics",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/C18-1310",
pages = "3658--3669",
abstract = "We present a corpus of spoken Dutch image descriptions, paired with two sets of eye-tracking data: Free viewing, where participants look at images without any particular purpose, and Description viewing, where we track eye movements while participants produce spoken descriptions of the images they are viewing. This paper describes the data collection procedure and the corpus itself, and provides an initial analysis of self-corrections in image descriptions. We also present two studies showing the potential of this data. Though these studies mainly serve as an example, we do find two interesting results: (1) the eye-tracking data for the description viewing task is more coherent than for the free-viewing task; (2) variation in image descriptions (also called {`}image specificity{'}; Jas and Parikh, 2015) is only moderately correlated across different languages. Our corpus can be used to gain a deeper understanding of the image description task, particularly how visual attention is correlated with the image description process.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-miltenburg-etal-2018-didec">
<titleInfo>
<title>DIDEC: The Dutch Image Description and Eye-tracking Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emiel</namePart>
<namePart type="family">van Miltenburg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ákos</namePart>
<namePart type="family">Kádár</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruud</namePart>
<namePart type="family">Koolen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emiel</namePart>
<namePart type="family">Krahmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Bender</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Isabelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a corpus of spoken Dutch image descriptions, paired with two sets of eye-tracking data: Free viewing, where participants look at images without any particular purpose, and Description viewing, where we track eye movements while participants produce spoken descriptions of the images they are viewing. This paper describes the data collection procedure and the corpus itself, and provides an initial analysis of self-corrections in image descriptions. We also present two studies showing the potential of this data. Though these studies mainly serve as an example, we do find two interesting results: (1) the eye-tracking data for the description viewing task is more coherent than for the free-viewing task; (2) variation in image descriptions (also called ‘image specificity’; Jas and Parikh, 2015) is only moderately correlated across different languages. Our corpus can be used to gain a deeper understanding of the image description task, particularly how visual attention is correlated with the image description process.</abstract>
<identifier type="citekey">van-miltenburg-etal-2018-didec</identifier>
<location>
<url>https://aclanthology.org/C18-1310</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>3658</start>
<end>3669</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DIDEC: The Dutch Image Description and Eye-tracking Corpus
%A van Miltenburg, Emiel
%A Kádár, Ákos
%A Koolen, Ruud
%A Krahmer, Emiel
%Y Bender, Emily M.
%Y Derczynski, Leon
%Y Isabelle, Pierre
%S Proceedings of the 27th International Conference on Computational Linguistics
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F van-miltenburg-etal-2018-didec
%X We present a corpus of spoken Dutch image descriptions, paired with two sets of eye-tracking data: Free viewing, where participants look at images without any particular purpose, and Description viewing, where we track eye movements while participants produce spoken descriptions of the images they are viewing. This paper describes the data collection procedure and the corpus itself, and provides an initial analysis of self-corrections in image descriptions. We also present two studies showing the potential of this data. Though these studies mainly serve as an example, we do find two interesting results: (1) the eye-tracking data for the description viewing task is more coherent than for the free-viewing task; (2) variation in image descriptions (also called ‘image specificity’; Jas and Parikh, 2015) is only moderately correlated across different languages. Our corpus can be used to gain a deeper understanding of the image description task, particularly how visual attention is correlated with the image description process.
%U https://aclanthology.org/C18-1310
%P 3658-3669
Markdown (Informal)
[DIDEC: The Dutch Image Description and Eye-tracking Corpus](https://aclanthology.org/C18-1310) (van Miltenburg et al., COLING 2018)
ACL
- Emiel van Miltenburg, Ákos Kádár, Ruud Koolen, and Emiel Krahmer. 2018. DIDEC: The Dutch Image Description and Eye-tracking Corpus. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3658–3669, Santa Fe, New Mexico, USA. Association for Computational Linguistics.