@inproceedings{chaimongkol-etal-2014-corpus,
title = "Corpus for Coreference Resolution on Scientific Papers",
author = "Chaimongkol, Panot and
Aizawa, Akiko and
Tateisi, Yuka",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/286_Paper.pdf",
pages = "3187--3190",
abstract = "The ever-growing number of published scientific papers prompts the need for automatic knowledge extraction to help scientists keep up with the state-of-the-art in their respective fields. To construct a good knowledge extraction system, annotated corpora in the scientific domain are required to train machine learning models. As described in this paper, we have constructed an annotated corpus for coreference resolution in multiple scientific domains, based on an existing corpus. We have modified the annotation scheme from Message Understanding Conference to better suit scientific texts. Then we applied that to the corpus. The annotated corpus is then compared with corpora in general domains in terms of distribution of resolution classes and performance of the Stanford Dcoref coreference resolver. Through these comparisons, we have demonstrated quantitatively that our manually annotated corpus differs from a general-domain corpus, which suggests deep differences between general-domain texts and scientific texts and which shows that different approaches can be made to tackle coreference resolution for general texts and scientific texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaimongkol-etal-2014-corpus">
<titleInfo>
<title>Corpus for Coreference Resolution on Scientific Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Panot</namePart>
<namePart type="family">Chaimongkol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Aizawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuka</namePart>
<namePart type="family">Tateisi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The ever-growing number of published scientific papers prompts the need for automatic knowledge extraction to help scientists keep up with the state-of-the-art in their respective fields. To construct a good knowledge extraction system, annotated corpora in the scientific domain are required to train machine learning models. As described in this paper, we have constructed an annotated corpus for coreference resolution in multiple scientific domains, based on an existing corpus. We have modified the annotation scheme from Message Understanding Conference to better suit scientific texts. Then we applied that to the corpus. The annotated corpus is then compared with corpora in general domains in terms of distribution of resolution classes and performance of the Stanford Dcoref coreference resolver. Through these comparisons, we have demonstrated quantitatively that our manually annotated corpus differs from a general-domain corpus, which suggests deep differences between general-domain texts and scientific texts and which shows that different approaches can be made to tackle coreference resolution for general texts and scientific texts.</abstract>
<identifier type="citekey">chaimongkol-etal-2014-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/286_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3187</start>
<end>3190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus for Coreference Resolution on Scientific Papers
%A Chaimongkol, Panot
%A Aizawa, Akiko
%A Tateisi, Yuka
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F chaimongkol-etal-2014-corpus
%X The ever-growing number of published scientific papers prompts the need for automatic knowledge extraction to help scientists keep up with the state-of-the-art in their respective fields. To construct a good knowledge extraction system, annotated corpora in the scientific domain are required to train machine learning models. As described in this paper, we have constructed an annotated corpus for coreference resolution in multiple scientific domains, based on an existing corpus. We have modified the annotation scheme from Message Understanding Conference to better suit scientific texts. Then we applied that to the corpus. The annotated corpus is then compared with corpora in general domains in terms of distribution of resolution classes and performance of the Stanford Dcoref coreference resolver. Through these comparisons, we have demonstrated quantitatively that our manually annotated corpus differs from a general-domain corpus, which suggests deep differences between general-domain texts and scientific texts and which shows that different approaches can be made to tackle coreference resolution for general texts and scientific texts.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/286_Paper.pdf
%P 3187-3190
Markdown (Informal)
[Corpus for Coreference Resolution on Scientific Papers](http://www.lrec-conf.org/proceedings/lrec2014/pdf/286_Paper.pdf) (Chaimongkol et al., LREC 2014)
ACL
- Panot Chaimongkol, Akiko Aizawa, and Yuka Tateisi. 2014. Corpus for Coreference Resolution on Scientific Papers. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3187–3190, Reykjavik, Iceland. European Language Resources Association (ELRA).