@inproceedings{hollink-etal-2016-corpus,
title = "A Corpus of Images and Text in Online News",
author = "Hollink, Laura and
Bedjeti, Adriatik and
van Harmelen, Martin and
Elliott, Desmond",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1219",
pages = "1377--1382",
abstract = "In recent years, several datasets have been released that include images and text, giving impulse to new methods that combine natural language processing and computer vision. However, there is a need for datasets of images in their natural textual context. The ION corpus contains 300K news articles published between August 2014 - 2015 in five online newspapers from two countries. The 1-year coverage over multiple publishers ensures a broad scope in terms of topics, image quality and editorial viewpoints. The corpus consists of JSON-LD files with the following data about each article: the original URL of the article on the news publisher{'}s website, the date of publication, the headline of the article, the URL of the image displayed with the article (if any), and the caption of that image. Neither the article text nor the images themselves are included in the corpus. Instead, the images are distributed as high-dimensional feature vectors extracted from a Convolutional Neural Network, anticipating their use in computer vision tasks. The article text is represented as a list of automatically generated entity and topic annotations in the form of Wikipedia/DBpedia pages. This facilitates the selection of subsets of the corpus for separate analysis or evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hollink-etal-2016-corpus">
<titleInfo>
<title>A Corpus of Images and Text in Online News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Hollink</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adriatik</namePart>
<namePart type="family">Bedjeti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">van Harmelen</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>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, several datasets have been released that include images and text, giving impulse to new methods that combine natural language processing and computer vision. However, there is a need for datasets of images in their natural textual context. The ION corpus contains 300K news articles published between August 2014 - 2015 in five online newspapers from two countries. The 1-year coverage over multiple publishers ensures a broad scope in terms of topics, image quality and editorial viewpoints. The corpus consists of JSON-LD files with the following data about each article: the original URL of the article on the news publisher’s website, the date of publication, the headline of the article, the URL of the image displayed with the article (if any), and the caption of that image. Neither the article text nor the images themselves are included in the corpus. Instead, the images are distributed as high-dimensional feature vectors extracted from a Convolutional Neural Network, anticipating their use in computer vision tasks. The article text is represented as a list of automatically generated entity and topic annotations in the form of Wikipedia/DBpedia pages. This facilitates the selection of subsets of the corpus for separate analysis or evaluation.</abstract>
<identifier type="citekey">hollink-etal-2016-corpus</identifier>
<location>
<url>https://aclanthology.org/L16-1219</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1377</start>
<end>1382</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus of Images and Text in Online News
%A Hollink, Laura
%A Bedjeti, Adriatik
%A van Harmelen, Martin
%A Elliott, Desmond
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F hollink-etal-2016-corpus
%X In recent years, several datasets have been released that include images and text, giving impulse to new methods that combine natural language processing and computer vision. However, there is a need for datasets of images in their natural textual context. The ION corpus contains 300K news articles published between August 2014 - 2015 in five online newspapers from two countries. The 1-year coverage over multiple publishers ensures a broad scope in terms of topics, image quality and editorial viewpoints. The corpus consists of JSON-LD files with the following data about each article: the original URL of the article on the news publisher’s website, the date of publication, the headline of the article, the URL of the image displayed with the article (if any), and the caption of that image. Neither the article text nor the images themselves are included in the corpus. Instead, the images are distributed as high-dimensional feature vectors extracted from a Convolutional Neural Network, anticipating their use in computer vision tasks. The article text is represented as a list of automatically generated entity and topic annotations in the form of Wikipedia/DBpedia pages. This facilitates the selection of subsets of the corpus for separate analysis or evaluation.
%U https://aclanthology.org/L16-1219
%P 1377-1382
Markdown (Informal)
[A Corpus of Images and Text in Online News](https://aclanthology.org/L16-1219) (Hollink et al., LREC 2016)
ACL
- Laura Hollink, Adriatik Bedjeti, Martin van Harmelen, and Desmond Elliott. 2016. A Corpus of Images and Text in Online News. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1377–1382, Portorož, Slovenia. European Language Resources Association (ELRA).