@inproceedings{chaudhary-etal-2020-efforts,
title = "Efforts Towards Developing a {T}amang {N}epali Machine Translation System",
author = "Chaudhary, Binaya Kumar and
Bal, Bal Krishna and
Baidar, Rasil",
editor = "Bhattacharyya, Pushpak and
Sharma, Dipti Misra and
Sangal, Rajeev",
booktitle = "Proceedings of the 17th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2020",
address = "Indian Institute of Technology Patna, Patna, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2020.icon-main.37",
pages = "281--286",
abstract = "The Tamang language is spoken mainly in Nepal, Sikkim, West Bengal, some parts of Assam, and the North East region of India. As per the 2011 census conducted by the Nepal Government, there are about 1.35 million Tamang speakers in Nepal itself. In this regard, a Machine Translation System for Tamang-Nepali language pair is significant both from research and practical outcomes in terms of enabling communication between the Tamang and the Nepali communities. In this work, we train the Transformer Neural Machine Translation (NMT) architecture with attention using a small hand-labeled or aligned Tamang-Nepali corpus (15K sentence pairs). Our preliminary results show BLEU scores of 27.74 for the Nepali→Tamang direction and 23.74 in the Tamang→Nepali direction. We are currently working on increasing the datasets as well as improving the model to obtain better BLEU scores. We also plan to extend the work to add the English language to the model, thus making it a trilingual Machine Translation System for Tamang-Nepali-English languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaudhary-etal-2020-efforts">
<titleInfo>
<title>Efforts Towards Developing a Tamang Nepali Machine Translation System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Binaya</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rasil</namePart>
<namePart type="family">Baidar</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 17th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</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">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajeev</namePart>
<namePart type="family">Sangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Indian Institute of Technology Patna, Patna, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Tamang language is spoken mainly in Nepal, Sikkim, West Bengal, some parts of Assam, and the North East region of India. As per the 2011 census conducted by the Nepal Government, there are about 1.35 million Tamang speakers in Nepal itself. In this regard, a Machine Translation System for Tamang-Nepali language pair is significant both from research and practical outcomes in terms of enabling communication between the Tamang and the Nepali communities. In this work, we train the Transformer Neural Machine Translation (NMT) architecture with attention using a small hand-labeled or aligned Tamang-Nepali corpus (15K sentence pairs). Our preliminary results show BLEU scores of 27.74 for the Nepali→Tamang direction and 23.74 in the Tamang→Nepali direction. We are currently working on increasing the datasets as well as improving the model to obtain better BLEU scores. We also plan to extend the work to add the English language to the model, thus making it a trilingual Machine Translation System for Tamang-Nepali-English languages.</abstract>
<identifier type="citekey">chaudhary-etal-2020-efforts</identifier>
<location>
<url>https://aclanthology.org/2020.icon-main.37</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>281</start>
<end>286</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efforts Towards Developing a Tamang Nepali Machine Translation System
%A Chaudhary, Binaya Kumar
%A Bal, Bal Krishna
%A Baidar, Rasil
%Y Bhattacharyya, Pushpak
%Y Sharma, Dipti Misra
%Y Sangal, Rajeev
%S Proceedings of the 17th International Conference on Natural Language Processing (ICON)
%D 2020
%8 December
%I NLP Association of India (NLPAI)
%C Indian Institute of Technology Patna, Patna, India
%F chaudhary-etal-2020-efforts
%X The Tamang language is spoken mainly in Nepal, Sikkim, West Bengal, some parts of Assam, and the North East region of India. As per the 2011 census conducted by the Nepal Government, there are about 1.35 million Tamang speakers in Nepal itself. In this regard, a Machine Translation System for Tamang-Nepali language pair is significant both from research and practical outcomes in terms of enabling communication between the Tamang and the Nepali communities. In this work, we train the Transformer Neural Machine Translation (NMT) architecture with attention using a small hand-labeled or aligned Tamang-Nepali corpus (15K sentence pairs). Our preliminary results show BLEU scores of 27.74 for the Nepali→Tamang direction and 23.74 in the Tamang→Nepali direction. We are currently working on increasing the datasets as well as improving the model to obtain better BLEU scores. We also plan to extend the work to add the English language to the model, thus making it a trilingual Machine Translation System for Tamang-Nepali-English languages.
%U https://aclanthology.org/2020.icon-main.37
%P 281-286
Markdown (Informal)
[Efforts Towards Developing a Tamang Nepali Machine Translation System](https://aclanthology.org/2020.icon-main.37) (Chaudhary et al., ICON 2020)
ACL