@inproceedings{kunchukuttan-etal-2014-shata,
title = "Shata-Anuvadak: Tackling Multiway Translation of {I}ndian Languages",
author = "Kunchukuttan, Anoop and
Mishra, Abhijit and
Chatterjee, Rajen and
Shah, Ritesh and
Bhattacharyya, Pushpak",
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 = "https://aclanthology.org/L14-1355/",
pages = "1781--1787",
abstract = "We present a compendium of 110 Statistical Machine Translation systems built from parallel corpora of 11 Indian languages belonging to both Indo-Aryan and Dravidian families. We analyze the relationship between translation accuracy and the language families involved. We feel that insights obtained from this analysis will provide guidelines for creating machine translation systems of specific Indian language pairs. We build phrase based systems and some extensions. Across multiple languages, we show improvements on the baseline phrase based systems using these extensions: (1) source side reordering for English-Indian language translation, and (2) transliteration of untranslated words for Indian language-Indian language translation. These enhancements harness shared characteristics of Indian languages. To stimulate similar innovation widely in the NLP community, we have made the trained models for these language pairs publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kunchukuttan-etal-2014-shata">
<titleInfo>
<title>Shata-Anuvadak: Tackling Multiway Translation of Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhijit</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</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>We present a compendium of 110 Statistical Machine Translation systems built from parallel corpora of 11 Indian languages belonging to both Indo-Aryan and Dravidian families. We analyze the relationship between translation accuracy and the language families involved. We feel that insights obtained from this analysis will provide guidelines for creating machine translation systems of specific Indian language pairs. We build phrase based systems and some extensions. Across multiple languages, we show improvements on the baseline phrase based systems using these extensions: (1) source side reordering for English-Indian language translation, and (2) transliteration of untranslated words for Indian language-Indian language translation. These enhancements harness shared characteristics of Indian languages. To stimulate similar innovation widely in the NLP community, we have made the trained models for these language pairs publicly available.</abstract>
<identifier type="citekey">kunchukuttan-etal-2014-shata</identifier>
<location>
<url>https://aclanthology.org/L14-1355/</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1781</start>
<end>1787</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Shata-Anuvadak: Tackling Multiway Translation of Indian Languages
%A Kunchukuttan, Anoop
%A Mishra, Abhijit
%A Chatterjee, Rajen
%A Shah, Ritesh
%A Bhattacharyya, Pushpak
%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 kunchukuttan-etal-2014-shata
%X We present a compendium of 110 Statistical Machine Translation systems built from parallel corpora of 11 Indian languages belonging to both Indo-Aryan and Dravidian families. We analyze the relationship between translation accuracy and the language families involved. We feel that insights obtained from this analysis will provide guidelines for creating machine translation systems of specific Indian language pairs. We build phrase based systems and some extensions. Across multiple languages, we show improvements on the baseline phrase based systems using these extensions: (1) source side reordering for English-Indian language translation, and (2) transliteration of untranslated words for Indian language-Indian language translation. These enhancements harness shared characteristics of Indian languages. To stimulate similar innovation widely in the NLP community, we have made the trained models for these language pairs publicly available.
%U https://aclanthology.org/L14-1355/
%P 1781-1787
Markdown (Informal)
[Shata-Anuvadak: Tackling Multiway Translation of Indian Languages](https://aclanthology.org/L14-1355/) (Kunchukuttan et al., LREC 2014)
ACL
- Anoop Kunchukuttan, Abhijit Mishra, Rajen Chatterjee, Ritesh Shah, and Pushpak Bhattacharyya. 2014. Shata-Anuvadak: Tackling Multiway Translation of Indian Languages. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1781–1787, Reykjavik, Iceland. European Language Resources Association (ELRA).