@inproceedings{ramesh-etal-2020-error,
title = "An Error-based Investigation of Statistical and Neural Machine Translation Performance on {H}indi-to-{T}amil and {E}nglish-to-{T}amil",
author = "Ramesh, Akshai and
Balavadhani Parthasa, Venkatesh and
Haque, Rejwanul and
Way, Andy",
booktitle = "Proceedings of the 7th Workshop on Asian Translation",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wat-1.22",
pages = "178--188",
abstract = "Statistical machine translation (SMT) was the state-of-the-art in machine translation (MT) research for more than two decades, but has since been superseded by neural MT (NMT). Despite producing state-of-the-art results in many translation tasks, neural models underperform in resource-poor scenarios. Despite some success, none of the present-day benchmarks that have tried to overcome this problem can be regarded as a universal solution to the problem of translation of many low-resource languages. In this work, we investigate the performance of phrase-based SMT (PB-SMT) and NMT on two rarely-tested low-resource language-pairs, English-to-Tamil and Hindi-to-Tamil, taking a specialised data domain (software localisation) into consideration. This paper demonstrates our findings including the identification of several issues of the current neural approaches to low-resource domain-specific text translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramesh-etal-2020-error">
<titleInfo>
<title>An Error-based Investigation of Statistical and Neural Machine Translation Performance on Hindi-to-Tamil and English-to-Tamil</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akshai</namePart>
<namePart type="family">Ramesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Venkatesh</namePart>
<namePart type="family">Balavadhani Parthasa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rejwanul</namePart>
<namePart type="family">Haque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Way</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Asian Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Statistical machine translation (SMT) was the state-of-the-art in machine translation (MT) research for more than two decades, but has since been superseded by neural MT (NMT). Despite producing state-of-the-art results in many translation tasks, neural models underperform in resource-poor scenarios. Despite some success, none of the present-day benchmarks that have tried to overcome this problem can be regarded as a universal solution to the problem of translation of many low-resource languages. In this work, we investigate the performance of phrase-based SMT (PB-SMT) and NMT on two rarely-tested low-resource language-pairs, English-to-Tamil and Hindi-to-Tamil, taking a specialised data domain (software localisation) into consideration. This paper demonstrates our findings including the identification of several issues of the current neural approaches to low-resource domain-specific text translation.</abstract>
<identifier type="citekey">ramesh-etal-2020-error</identifier>
<location>
<url>https://aclanthology.org/2020.wat-1.22</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>178</start>
<end>188</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Error-based Investigation of Statistical and Neural Machine Translation Performance on Hindi-to-Tamil and English-to-Tamil
%A Ramesh, Akshai
%A Balavadhani Parthasa, Venkatesh
%A Haque, Rejwanul
%A Way, Andy
%S Proceedings of the 7th Workshop on Asian Translation
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F ramesh-etal-2020-error
%X Statistical machine translation (SMT) was the state-of-the-art in machine translation (MT) research for more than two decades, but has since been superseded by neural MT (NMT). Despite producing state-of-the-art results in many translation tasks, neural models underperform in resource-poor scenarios. Despite some success, none of the present-day benchmarks that have tried to overcome this problem can be regarded as a universal solution to the problem of translation of many low-resource languages. In this work, we investigate the performance of phrase-based SMT (PB-SMT) and NMT on two rarely-tested low-resource language-pairs, English-to-Tamil and Hindi-to-Tamil, taking a specialised data domain (software localisation) into consideration. This paper demonstrates our findings including the identification of several issues of the current neural approaches to low-resource domain-specific text translation.
%U https://aclanthology.org/2020.wat-1.22
%P 178-188
Markdown (Informal)
[An Error-based Investigation of Statistical and Neural Machine Translation Performance on Hindi-to-Tamil and English-to-Tamil](https://aclanthology.org/2020.wat-1.22) (Ramesh et al., WAT 2020)
ACL