@inproceedings{yeka-etal-2014-benchmarking,
title = "Benchmarking of {E}nglish-{H}indi parallel corpora",
author = "Yeka, Jayendra Rakesh and
Kolachina, Prasanth and
Sharma, Dipti Misra",
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/1137_Paper.pdf",
pages = "1812--1818",
abstract = "In this paper we present several parallel corpora for English{\^a}Hindi and talk about their natures and domains. We also discuss briefly a few previous attempts in MT for translation from English to Hindi. The lack of uniformly annotated data makes it difficult to compare these attempts and precisely analyze their strengths and shortcomings. With this in mind, we propose a standard pipeline to provide uniform linguistic annotations to these resources using state-of-art NLP technologies. We conclude the paper by presenting evaluation scores of different statistical MT systems on the corpora detailed in this paper for English{\^a}Hindi and present the proposed plans for future work. We hope that both these annotated parallel corpora resources and MT systems will serve as benchmarks for future approaches to MT in English{\^a}Hindi. This was and remains the main motivation for the attempts detailed in this paper.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yeka-etal-2014-benchmarking">
<titleInfo>
<title>Benchmarking of English-Hindi parallel corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jayendra</namePart>
<namePart type="given">Rakesh</namePart>
<namePart type="family">Yeka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasanth</namePart>
<namePart type="family">Kolachina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</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>In this paper we present several parallel corpora for EnglishâHindi and talk about their natures and domains. We also discuss briefly a few previous attempts in MT for translation from English to Hindi. The lack of uniformly annotated data makes it difficult to compare these attempts and precisely analyze their strengths and shortcomings. With this in mind, we propose a standard pipeline to provide uniform linguistic annotations to these resources using state-of-art NLP technologies. We conclude the paper by presenting evaluation scores of different statistical MT systems on the corpora detailed in this paper for EnglishâHindi and present the proposed plans for future work. We hope that both these annotated parallel corpora resources and MT systems will serve as benchmarks for future approaches to MT in EnglishâHindi. This was and remains the main motivation for the attempts detailed in this paper.</abstract>
<identifier type="citekey">yeka-etal-2014-benchmarking</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1137_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1812</start>
<end>1818</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking of English-Hindi parallel corpora
%A Yeka, Jayendra Rakesh
%A Kolachina, Prasanth
%A Sharma, Dipti Misra
%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 yeka-etal-2014-benchmarking
%X In this paper we present several parallel corpora for EnglishâHindi and talk about their natures and domains. We also discuss briefly a few previous attempts in MT for translation from English to Hindi. The lack of uniformly annotated data makes it difficult to compare these attempts and precisely analyze their strengths and shortcomings. With this in mind, we propose a standard pipeline to provide uniform linguistic annotations to these resources using state-of-art NLP technologies. We conclude the paper by presenting evaluation scores of different statistical MT systems on the corpora detailed in this paper for EnglishâHindi and present the proposed plans for future work. We hope that both these annotated parallel corpora resources and MT systems will serve as benchmarks for future approaches to MT in EnglishâHindi. This was and remains the main motivation for the attempts detailed in this paper.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1137_Paper.pdf
%P 1812-1818
Markdown (Informal)
[Benchmarking of English-Hindi parallel corpora](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1137_Paper.pdf) (Yeka et al., LREC 2014)
ACL
- Jayendra Rakesh Yeka, Prasanth Kolachina, and Dipti Misra Sharma. 2014. Benchmarking of English-Hindi parallel corpora. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1812–1818, Reykjavik, Iceland. European Language Resources Association (ELRA).