@inproceedings{van-miltenburg-etal-2017-cross,
title = "Cross-linguistic differences and similarities in image descriptions",
author = "van Miltenburg, Emiel and
Elliott, Desmond and
Vossen, Piek",
editor = "Alonso, Jose M. and
Bugar{\'\i}n, Alberto and
Reiter, Ehud",
booktitle = "Proceedings of the 10th International Conference on Natural Language Generation",
month = sep,
year = "2017",
address = "Santiago de Compostela, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-3503",
doi = "10.18653/v1/W17-3503",
pages = "21--30",
abstract = "Automatic image description systems are commonly trained and evaluated on large image description datasets. Recently, researchers have started to collect such datasets for languages other than English. An unexplored question is how different these datasets are from English and, if there are any differences, what causes them to differ. This paper provides a cross-linguistic comparison of Dutch, English, and German image descriptions. We find that these descriptions are similar in many respects, but the familiarity of crowd workers with the subjects of the images has a noticeable influence on the specificity of the descriptions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-miltenburg-etal-2017-cross">
<titleInfo>
<title>Cross-linguistic differences and similarities in image descriptions</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">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Alonso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Bugarín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santiago de Compostela, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic image description systems are commonly trained and evaluated on large image description datasets. Recently, researchers have started to collect such datasets for languages other than English. An unexplored question is how different these datasets are from English and, if there are any differences, what causes them to differ. This paper provides a cross-linguistic comparison of Dutch, English, and German image descriptions. We find that these descriptions are similar in many respects, but the familiarity of crowd workers with the subjects of the images has a noticeable influence on the specificity of the descriptions.</abstract>
<identifier type="citekey">van-miltenburg-etal-2017-cross</identifier>
<identifier type="doi">10.18653/v1/W17-3503</identifier>
<location>
<url>https://aclanthology.org/W17-3503</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>21</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-linguistic differences and similarities in image descriptions
%A van Miltenburg, Emiel
%A Elliott, Desmond
%A Vossen, Piek
%Y Alonso, Jose M.
%Y Bugarín, Alberto
%Y Reiter, Ehud
%S Proceedings of the 10th International Conference on Natural Language Generation
%D 2017
%8 September
%I Association for Computational Linguistics
%C Santiago de Compostela, Spain
%F van-miltenburg-etal-2017-cross
%X Automatic image description systems are commonly trained and evaluated on large image description datasets. Recently, researchers have started to collect such datasets for languages other than English. An unexplored question is how different these datasets are from English and, if there are any differences, what causes them to differ. This paper provides a cross-linguistic comparison of Dutch, English, and German image descriptions. We find that these descriptions are similar in many respects, but the familiarity of crowd workers with the subjects of the images has a noticeable influence on the specificity of the descriptions.
%R 10.18653/v1/W17-3503
%U https://aclanthology.org/W17-3503
%U https://doi.org/10.18653/v1/W17-3503
%P 21-30
Markdown (Informal)
[Cross-linguistic differences and similarities in image descriptions](https://aclanthology.org/W17-3503) (van Miltenburg et al., INLG 2017)
ACL