@inproceedings{nanba-etal-2012-automatic,
title = "Automatic Translation of Scholarly Terms into Patent Terms Using Synonym Extraction Techniques",
author = "Nanba, Hidetsugu and
Takezawa, Toshiyuki and
Uchiyama, Kiyoko and
Aizawa, Akiko",
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/1043_Paper.pdf",
pages = "3447--3451",
abstract = "Retrieving research papers and patents is important for any researcher assessing the scope of a field with high industrial relevance. However, the terms used in patents are often more abstract or creative than those used in research papers, because they are intended to widen the scope of claims. Therefore, a method is required for translating scholarly terms into patent terms. In this paper, we propose six methods for translating scholarly terms into patent terms using two synonym extraction methods: a statistical machine translation (SMT)-based method and a distributional similarity (DS)-based method. We conducted experiments to confirm the effectiveness of our method using the dataset of the Patent Mining Task from the NTCIR-7 Workshop. The aim of the task was to classify Japanese language research papers (pairs of titles and abstracts) using the IPC system at the subclass (third level), main group (fourth level), and subgroup (the fifth and most detailed level). The results showed that an SMT-based method (SMT{\_}ABST+IDF) performed best at the subgroup level, whereas a DS-based method (DS+IDF) performed best at the subclass level.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nanba-etal-2012-automatic">
<titleInfo>
<title>Automatic Translation of Scholarly Terms into Patent Terms Using Synonym Extraction Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hidetsugu</namePart>
<namePart type="family">Nanba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiyuki</namePart>
<namePart type="family">Takezawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiyoko</namePart>
<namePart type="family">Uchiyama</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>
<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>Retrieving research papers and patents is important for any researcher assessing the scope of a field with high industrial relevance. However, the terms used in patents are often more abstract or creative than those used in research papers, because they are intended to widen the scope of claims. Therefore, a method is required for translating scholarly terms into patent terms. In this paper, we propose six methods for translating scholarly terms into patent terms using two synonym extraction methods: a statistical machine translation (SMT)-based method and a distributional similarity (DS)-based method. We conducted experiments to confirm the effectiveness of our method using the dataset of the Patent Mining Task from the NTCIR-7 Workshop. The aim of the task was to classify Japanese language research papers (pairs of titles and abstracts) using the IPC system at the subclass (third level), main group (fourth level), and subgroup (the fifth and most detailed level). The results showed that an SMT-based method (SMT_ABST+IDF) performed best at the subgroup level, whereas a DS-based method (DS+IDF) performed best at the subclass level.</abstract>
<identifier type="citekey">nanba-etal-2012-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1043_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3447</start>
<end>3451</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Translation of Scholarly Terms into Patent Terms Using Synonym Extraction Techniques
%A Nanba, Hidetsugu
%A Takezawa, Toshiyuki
%A Uchiyama, Kiyoko
%A Aizawa, Akiko
%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 nanba-etal-2012-automatic
%X Retrieving research papers and patents is important for any researcher assessing the scope of a field with high industrial relevance. However, the terms used in patents are often more abstract or creative than those used in research papers, because they are intended to widen the scope of claims. Therefore, a method is required for translating scholarly terms into patent terms. In this paper, we propose six methods for translating scholarly terms into patent terms using two synonym extraction methods: a statistical machine translation (SMT)-based method and a distributional similarity (DS)-based method. We conducted experiments to confirm the effectiveness of our method using the dataset of the Patent Mining Task from the NTCIR-7 Workshop. The aim of the task was to classify Japanese language research papers (pairs of titles and abstracts) using the IPC system at the subclass (third level), main group (fourth level), and subgroup (the fifth and most detailed level). The results showed that an SMT-based method (SMT_ABST+IDF) performed best at the subgroup level, whereas a DS-based method (DS+IDF) performed best at the subclass level.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1043_Paper.pdf
%P 3447-3451
Markdown (Informal)
[Automatic Translation of Scholarly Terms into Patent Terms Using Synonym Extraction Techniques](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1043_Paper.pdf) (Nanba et al., LREC 2012)
ACL