@inproceedings{bongelli-etal-2012-corpus,
title = "A Corpus of Scientific Biomedical Texts Spanning over 168 Years Annotated for Uncertainty",
author = "Bongelli, Ramona and
Canestrari, Carla and
Riccioni, Ilaria and
Zuczkowski, Andrzej and
Buldorini, Cinzia and
Pietrobon, Ricardo and
Lavelli, Alberto and
Magnini, Bernardo",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/823_Paper.pdf",
pages = "2009--2014",
abstract = "Uncertainty language permeates biomedical research and is fundamental for the computer interpretation of unstructured text. And yet, a coherent, cognitive-based theory to interpret Uncertainty language and guide Natural Language Processing is, to our knowledge, non-existing. The aim of our project was therefore to detect and annotate Uncertainty markers ― which play a significant role in building knowledge or beliefs in readers' minds ― in a biomedical research corpus. Our corpus includes 80 manually annotated articles from the British Medical Journal randomly sampled from a 168-year period. Uncertainty markers have been classified according to a theoretical framework based on a combined linguistic and cognitive theory. The corpus was manually annotated according to such principles. We performed preliminary experiments to assess the manually annotated corpus and establish a baseline for the automatic detection of Uncertainty markers. The results of the experiments show that most of the Uncertainty markers can be recognized with good accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bongelli-etal-2012-corpus">
<titleInfo>
<title>A Corpus of Scientific Biomedical Texts Spanning over 168 Years Annotated for Uncertainty</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramona</namePart>
<namePart type="family">Bongelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Canestrari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilaria</namePart>
<namePart type="family">Riccioni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrzej</namePart>
<namePart type="family">Zuczkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cinzia</namePart>
<namePart type="family">Buldorini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Pietrobon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernardo</namePart>
<namePart type="family">Magnini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Uncertainty language permeates biomedical research and is fundamental for the computer interpretation of unstructured text. And yet, a coherent, cognitive-based theory to interpret Uncertainty language and guide Natural Language Processing is, to our knowledge, non-existing. The aim of our project was therefore to detect and annotate Uncertainty markers ― which play a significant role in building knowledge or beliefs in readers’ minds ― in a biomedical research corpus. Our corpus includes 80 manually annotated articles from the British Medical Journal randomly sampled from a 168-year period. Uncertainty markers have been classified according to a theoretical framework based on a combined linguistic and cognitive theory. The corpus was manually annotated according to such principles. We performed preliminary experiments to assess the manually annotated corpus and establish a baseline for the automatic detection of Uncertainty markers. The results of the experiments show that most of the Uncertainty markers can be recognized with good accuracy.</abstract>
<identifier type="citekey">bongelli-etal-2012-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/823_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2009</start>
<end>2014</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus of Scientific Biomedical Texts Spanning over 168 Years Annotated for Uncertainty
%A Bongelli, Ramona
%A Canestrari, Carla
%A Riccioni, Ilaria
%A Zuczkowski, Andrzej
%A Buldorini, Cinzia
%A Pietrobon, Ricardo
%A Lavelli, Alberto
%A Magnini, Bernardo
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F bongelli-etal-2012-corpus
%X Uncertainty language permeates biomedical research and is fundamental for the computer interpretation of unstructured text. And yet, a coherent, cognitive-based theory to interpret Uncertainty language and guide Natural Language Processing is, to our knowledge, non-existing. The aim of our project was therefore to detect and annotate Uncertainty markers ― which play a significant role in building knowledge or beliefs in readers’ minds ― in a biomedical research corpus. Our corpus includes 80 manually annotated articles from the British Medical Journal randomly sampled from a 168-year period. Uncertainty markers have been classified according to a theoretical framework based on a combined linguistic and cognitive theory. The corpus was manually annotated according to such principles. We performed preliminary experiments to assess the manually annotated corpus and establish a baseline for the automatic detection of Uncertainty markers. The results of the experiments show that most of the Uncertainty markers can be recognized with good accuracy.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/823_Paper.pdf
%P 2009-2014
Markdown (Informal)
[A Corpus of Scientific Biomedical Texts Spanning over 168 Years Annotated for Uncertainty](http://www.lrec-conf.org/proceedings/lrec2012/pdf/823_Paper.pdf) (Bongelli et al., LREC 2012)
ACL
- Ramona Bongelli, Carla Canestrari, Ilaria Riccioni, Andrzej Zuczkowski, Cinzia Buldorini, Ricardo Pietrobon, Alberto Lavelli, and Bernardo Magnini. 2012. A Corpus of Scientific Biomedical Texts Spanning over 168 Years Annotated for Uncertainty. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2009–2014, Istanbul, Turkey. European Language Resources Association (ELRA).