@inproceedings{demir-etal-2012-turkish,
title = "{T}urkish Paraphrase Corpus",
author = "Demir, Seniz and
El-Kahlout, {\.I}lknur Durgar and
Unal, Erdem and
Kaya, Hamza",
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/968_Paper.pdf",
pages = "4087--4091",
abstract = "Paraphrases are alternative syntactic forms in the same language expressing the same semantic content. Speakers of all languages are inherently familiar with paraphrases at different levels of granularity (lexical, phrasal, and sentential). For quite some time, the concept of paraphrasing is getting a growing attention by the research community and its potential use in several natural language processing applications (such as text summarization and machine translation) is being investigated. In this paper, we present, what is to our best knowledge, the first Turkish paraphrase corpus. The corpus is gleaned from four different sources and currently contains 1270 paraphrase pairs. All paraphrase pairs are carefully annotated by native Turkish speakers with the identified semantic correspondences between paraphrases. The work for expanding the corpus is still under way.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="demir-etal-2012-turkish">
<titleInfo>
<title>Turkish Paraphrase Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seniz</namePart>
<namePart type="family">Demir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">İlknur</namePart>
<namePart type="given">Durgar</namePart>
<namePart type="family">El-Kahlout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erdem</namePart>
<namePart type="family">Unal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamza</namePart>
<namePart type="family">Kaya</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>Paraphrases are alternative syntactic forms in the same language expressing the same semantic content. Speakers of all languages are inherently familiar with paraphrases at different levels of granularity (lexical, phrasal, and sentential). For quite some time, the concept of paraphrasing is getting a growing attention by the research community and its potential use in several natural language processing applications (such as text summarization and machine translation) is being investigated. In this paper, we present, what is to our best knowledge, the first Turkish paraphrase corpus. The corpus is gleaned from four different sources and currently contains 1270 paraphrase pairs. All paraphrase pairs are carefully annotated by native Turkish speakers with the identified semantic correspondences between paraphrases. The work for expanding the corpus is still under way.</abstract>
<identifier type="citekey">demir-etal-2012-turkish</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/968_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>4087</start>
<end>4091</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Turkish Paraphrase Corpus
%A Demir, Seniz
%A El-Kahlout, İlknur Durgar
%A Unal, Erdem
%A Kaya, Hamza
%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 demir-etal-2012-turkish
%X Paraphrases are alternative syntactic forms in the same language expressing the same semantic content. Speakers of all languages are inherently familiar with paraphrases at different levels of granularity (lexical, phrasal, and sentential). For quite some time, the concept of paraphrasing is getting a growing attention by the research community and its potential use in several natural language processing applications (such as text summarization and machine translation) is being investigated. In this paper, we present, what is to our best knowledge, the first Turkish paraphrase corpus. The corpus is gleaned from four different sources and currently contains 1270 paraphrase pairs. All paraphrase pairs are carefully annotated by native Turkish speakers with the identified semantic correspondences between paraphrases. The work for expanding the corpus is still under way.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/968_Paper.pdf
%P 4087-4091
Markdown (Informal)
[Turkish Paraphrase Corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/968_Paper.pdf) (Demir et al., LREC 2012)
ACL
- Seniz Demir, İlknur Durgar El-Kahlout, Erdem Unal, and Hamza Kaya. 2012. Turkish Paraphrase Corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 4087–4091, Istanbul, Turkey. European Language Resources Association (ELRA).