@inproceedings{galibert-etal-2010-hybrid,
title = "Hybrid Citation Extraction from Patents",
author = "Galibert, Olivier and
Rosset, Sophie and
Tannier, Xavier and
Grandry, Fanny",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/81_Paper.pdf",
abstract = "The Quaero project organized a set of evaluations of Named Entity recognition systems in 2009. One of the sub-tasks consists in extracting citations from patents, i.e. references to other documents, either other patents or general literature from English-language patents. We present in this paper the participation of LIMSI in this evaluation, with a complete system description and the evaluation results. The corpus shown that patent and non-patent citations have a very different nature. We then separated references to other patents and to general literature papers and we created a hybrid system. For patent citations, the system used rule-based expert knowledge on the form of regular expressions. The system for detecting non-patent citations, on the other hand, is purely stochastic (machine learning with CRF++). Then we mixed both approaches to provide a single output. 4 teams participated to this task and our system obtained the best results of this evaluation campaign, even if the difference between the first two systems is poorly significant.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galibert-etal-2010-hybrid">
<titleInfo>
<title>Hybrid Citation Extraction from Patents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Galibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Rosset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xavier</namePart>
<namePart type="family">Tannier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fanny</namePart>
<namePart type="family">Grandry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Quaero project organized a set of evaluations of Named Entity recognition systems in 2009. One of the sub-tasks consists in extracting citations from patents, i.e. references to other documents, either other patents or general literature from English-language patents. We present in this paper the participation of LIMSI in this evaluation, with a complete system description and the evaluation results. The corpus shown that patent and non-patent citations have a very different nature. We then separated references to other patents and to general literature papers and we created a hybrid system. For patent citations, the system used rule-based expert knowledge on the form of regular expressions. The system for detecting non-patent citations, on the other hand, is purely stochastic (machine learning with CRF++). Then we mixed both approaches to provide a single output. 4 teams participated to this task and our system obtained the best results of this evaluation campaign, even if the difference between the first two systems is poorly significant.</abstract>
<identifier type="citekey">galibert-etal-2010-hybrid</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/81_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hybrid Citation Extraction from Patents
%A Galibert, Olivier
%A Rosset, Sophie
%A Tannier, Xavier
%A Grandry, Fanny
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F galibert-etal-2010-hybrid
%X The Quaero project organized a set of evaluations of Named Entity recognition systems in 2009. One of the sub-tasks consists in extracting citations from patents, i.e. references to other documents, either other patents or general literature from English-language patents. We present in this paper the participation of LIMSI in this evaluation, with a complete system description and the evaluation results. The corpus shown that patent and non-patent citations have a very different nature. We then separated references to other patents and to general literature papers and we created a hybrid system. For patent citations, the system used rule-based expert knowledge on the form of regular expressions. The system for detecting non-patent citations, on the other hand, is purely stochastic (machine learning with CRF++). Then we mixed both approaches to provide a single output. 4 teams participated to this task and our system obtained the best results of this evaluation campaign, even if the difference between the first two systems is poorly significant.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/81_Paper.pdf
Markdown (Informal)
[Hybrid Citation Extraction from Patents](http://www.lrec-conf.org/proceedings/lrec2010/pdf/81_Paper.pdf) (Galibert et al., LREC 2010)
ACL
- Olivier Galibert, Sophie Rosset, Xavier Tannier, and Fanny Grandry. 2010. Hybrid Citation Extraction from Patents. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).