@inproceedings{kunchukuttan-etal-2021-large,
title = "A Large-scale Evaluation of Neural Machine Transliteration for {I}ndic Languages",
author = "Kunchukuttan, Anoop and
Jain, Siddharth and
Kejriwal, Rahul",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.303",
doi = "10.18653/v1/2021.eacl-main.303",
pages = "3469--3475",
abstract = "We take up the task of large-scale evaluation of neural machine transliteration between English and Indic languages, with a focus on multilingual transliteration to utilize orthographic similarity between Indian languages. We create a corpus of 600K word pairs mined from parallel translation corpora and monolingual corpora, which is the largest transliteration corpora for Indian languages mined from public sources. We perform a detailed analysis of multilingual transliteration and propose an improved multilingual training recipe for Indic languages. We analyze various factors affecting transliteration quality like language family, transliteration direction and word origin.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kunchukuttan-etal-2021-large">
<titleInfo>
<title>A Large-scale Evaluation of Neural Machine Transliteration for Indic 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">Siddharth</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Kejriwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We take up the task of large-scale evaluation of neural machine transliteration between English and Indic languages, with a focus on multilingual transliteration to utilize orthographic similarity between Indian languages. We create a corpus of 600K word pairs mined from parallel translation corpora and monolingual corpora, which is the largest transliteration corpora for Indian languages mined from public sources. We perform a detailed analysis of multilingual transliteration and propose an improved multilingual training recipe for Indic languages. We analyze various factors affecting transliteration quality like language family, transliteration direction and word origin.</abstract>
<identifier type="citekey">kunchukuttan-etal-2021-large</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.303</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.303</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>3469</start>
<end>3475</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large-scale Evaluation of Neural Machine Transliteration for Indic Languages
%A Kunchukuttan, Anoop
%A Jain, Siddharth
%A Kejriwal, Rahul
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F kunchukuttan-etal-2021-large
%X We take up the task of large-scale evaluation of neural machine transliteration between English and Indic languages, with a focus on multilingual transliteration to utilize orthographic similarity between Indian languages. We create a corpus of 600K word pairs mined from parallel translation corpora and monolingual corpora, which is the largest transliteration corpora for Indian languages mined from public sources. We perform a detailed analysis of multilingual transliteration and propose an improved multilingual training recipe for Indic languages. We analyze various factors affecting transliteration quality like language family, transliteration direction and word origin.
%R 10.18653/v1/2021.eacl-main.303
%U https://aclanthology.org/2021.eacl-main.303
%U https://doi.org/10.18653/v1/2021.eacl-main.303
%P 3469-3475
Markdown (Informal)
[A Large-scale Evaluation of Neural Machine Transliteration for Indic Languages](https://aclanthology.org/2021.eacl-main.303) (Kunchukuttan et al., EACL 2021)
ACL