@inproceedings{koneru-etal-2021-unsupervised,
title = "Unsupervised Machine Translation On {D}ravidian Languages",
author = "Koneru, Sai and
Liu, Danni and
Niehues, Jan",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Kumar M, Anand and
Krishnamurthy, Parameswari and
Sherly, Elizabeth",
booktitle = "Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages",
month = apr,
year = "2021",
address = "Kyiv",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.dravidianlangtech-1.7",
pages = "55--64",
abstract = "Unsupervised Neural Machine translation (UNMT) is beneficial especially for under-resourced languages such as from the Dravidian family. They learn to translate between the source and target, relying solely on only monolingual corpora. However, UNMT systems fail in scenarios that occur often when dealing with low resource languages. Recent works have achieved state-of-the-art results by adding auxiliary parallel data with similar languages. In this work, we focus on unsupervised translation between English and Kannada by using limited amounts of auxiliary data between English and other Dravidian languages. We show that transliteration is essential in unsupervised translation between Dravidian languages, as they do not share a common writing system. We explore several model architectures that use the auxiliary data in order to maximize knowledge sharing and enable UNMT for dissimilar language pairs. We show from our experiments it is crucial for Kannada and reference languages to be similar. Further, we propose a method to measure language similarity to choose the most beneficial reference languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koneru-etal-2021-unsupervised">
<titleInfo>
<title>Unsupervised Machine Translation On Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="family">Koneru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danni</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</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 First Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="family">Kumar M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unsupervised Neural Machine translation (UNMT) is beneficial especially for under-resourced languages such as from the Dravidian family. They learn to translate between the source and target, relying solely on only monolingual corpora. However, UNMT systems fail in scenarios that occur often when dealing with low resource languages. Recent works have achieved state-of-the-art results by adding auxiliary parallel data with similar languages. In this work, we focus on unsupervised translation between English and Kannada by using limited amounts of auxiliary data between English and other Dravidian languages. We show that transliteration is essential in unsupervised translation between Dravidian languages, as they do not share a common writing system. We explore several model architectures that use the auxiliary data in order to maximize knowledge sharing and enable UNMT for dissimilar language pairs. We show from our experiments it is crucial for Kannada and reference languages to be similar. Further, we propose a method to measure language similarity to choose the most beneficial reference languages.</abstract>
<identifier type="citekey">koneru-etal-2021-unsupervised</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.7</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>55</start>
<end>64</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Machine Translation On Dravidian Languages
%A Koneru, Sai
%A Liu, Danni
%A Niehues, Jan
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Kumar M, Anand
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%S Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv
%F koneru-etal-2021-unsupervised
%X Unsupervised Neural Machine translation (UNMT) is beneficial especially for under-resourced languages such as from the Dravidian family. They learn to translate between the source and target, relying solely on only monolingual corpora. However, UNMT systems fail in scenarios that occur often when dealing with low resource languages. Recent works have achieved state-of-the-art results by adding auxiliary parallel data with similar languages. In this work, we focus on unsupervised translation between English and Kannada by using limited amounts of auxiliary data between English and other Dravidian languages. We show that transliteration is essential in unsupervised translation between Dravidian languages, as they do not share a common writing system. We explore several model architectures that use the auxiliary data in order to maximize knowledge sharing and enable UNMT for dissimilar language pairs. We show from our experiments it is crucial for Kannada and reference languages to be similar. Further, we propose a method to measure language similarity to choose the most beneficial reference languages.
%U https://aclanthology.org/2021.dravidianlangtech-1.7
%P 55-64
Markdown (Informal)
[Unsupervised Machine Translation On Dravidian Languages](https://aclanthology.org/2021.dravidianlangtech-1.7) (Koneru et al., DravidianLangTech 2021)
ACL