@inproceedings{shmanina-etal-2016-corpus,
title = "A Corpus of Tables in Full-Text Biomedical Research Publications",
author = "Shmanina, Tatyana and
Zukerman, Ingrid and
Cheam, Ai Lee and
Bochynek, Thomas and
Cavedon, Lawrence",
editor = "Ananiadou, Sophia and
Batista-Navarro, Riza and
Cohen, Kevin Bretonnel and
Demner-Fushman, Dina and
Thompson, Paul",
booktitle = "Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining ({B}io{T}xt{M}2016)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-5108",
pages = "70--79",
abstract = "The development of text mining techniques for biomedical research literature has received increased attention in recent times. However, most of these techniques focus on prose, while much important biomedical data reside in tables. In this paper, we present a corpus created to serve as a gold standard for the development and evaluation of techniques for the automatic extraction of information from biomedical tables. We describe the guidelines used for corpus annotation and the manner in which they were developed. The high inter-annotator agreement achieved on the corpus, and the generic nature of our annotation approach, suggest that the developed guidelines can serve as a general framework for table annotation in biomedical and other scientific domains. The annotated corpus and the guidelines are available at \url{http://www.csse.monash.edu.au/research/umnl/data/index.shtml}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shmanina-etal-2016-corpus">
<titleInfo>
<title>A Corpus of Tables in Full-Text Biomedical Research Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatyana</namePart>
<namePart type="family">Shmanina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingrid</namePart>
<namePart type="family">Zukerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ai</namePart>
<namePart type="given">Lee</namePart>
<namePart type="family">Cheam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Bochynek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Cavedon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riza</namePart>
<namePart type="family">Batista-Navarro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The development of text mining techniques for biomedical research literature has received increased attention in recent times. However, most of these techniques focus on prose, while much important biomedical data reside in tables. In this paper, we present a corpus created to serve as a gold standard for the development and evaluation of techniques for the automatic extraction of information from biomedical tables. We describe the guidelines used for corpus annotation and the manner in which they were developed. The high inter-annotator agreement achieved on the corpus, and the generic nature of our annotation approach, suggest that the developed guidelines can serve as a general framework for table annotation in biomedical and other scientific domains. The annotated corpus and the guidelines are available at http://www.csse.monash.edu.au/research/umnl/data/index.shtml.</abstract>
<identifier type="citekey">shmanina-etal-2016-corpus</identifier>
<location>
<url>https://aclanthology.org/W16-5108</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>70</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus of Tables in Full-Text Biomedical Research Publications
%A Shmanina, Tatyana
%A Zukerman, Ingrid
%A Cheam, Ai Lee
%A Bochynek, Thomas
%A Cavedon, Lawrence
%Y Ananiadou, Sophia
%Y Batista-Navarro, Riza
%Y Cohen, Kevin Bretonnel
%Y Demner-Fushman, Dina
%Y Thompson, Paul
%S Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F shmanina-etal-2016-corpus
%X The development of text mining techniques for biomedical research literature has received increased attention in recent times. However, most of these techniques focus on prose, while much important biomedical data reside in tables. In this paper, we present a corpus created to serve as a gold standard for the development and evaluation of techniques for the automatic extraction of information from biomedical tables. We describe the guidelines used for corpus annotation and the manner in which they were developed. The high inter-annotator agreement achieved on the corpus, and the generic nature of our annotation approach, suggest that the developed guidelines can serve as a general framework for table annotation in biomedical and other scientific domains. The annotated corpus and the guidelines are available at http://www.csse.monash.edu.au/research/umnl/data/index.shtml.
%U https://aclanthology.org/W16-5108
%P 70-79
Markdown (Informal)
[A Corpus of Tables in Full-Text Biomedical Research Publications](https://aclanthology.org/W16-5108) (Shmanina et al., 2016)
ACL
- Tatyana Shmanina, Ingrid Zukerman, Ai Lee Cheam, Thomas Bochynek, and Lawrence Cavedon. 2016. A Corpus of Tables in Full-Text Biomedical Research Publications. In Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016), pages 70–79, Osaka, Japan. The COLING 2016 Organizing Committee.