@inproceedings{khenglawt-etal-2022-language,
title = "Language Resource Building and {E}nglish-to-Mizo Neural Machine Translation Encountering Tonal Words",
author = "Khenglawt, Vanlalmuansangi and
Laskar, Sahinur Rahman and
Pal, Santanu and
Pakray, Partha and
Khan, Ajoy Kumar",
editor = "Jha, Girish Nath and
L., Sobha and
Bali, Kalika and
Ojha, Atul Kr.",
booktitle = "Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.wildre-1.9",
pages = "48--54",
abstract = "Multilingual country like India has an enormous linguistic diversity and has an increasing demand towards developing language resources such that it will outreach in various natural language processing applications like machine translation. Low-resource language translation possesses challenges in the field of machine translation. The challenges include the availability of corpus and differences in linguistic information. This paper investigates a low-resource language pair, English-to-Mizo exploring neural machine translation by contributing an Indian language resource, i.e., English-Mizo corpus. In this work, we explore one of the main challenges to tackling tonal words existing in the Mizo language, as they add to the complexity on top of low-resource challenges for any natural language processing task. Our approach improves translation accuracy by encountering tonal words of Mizo and achieved a state-of-the-art result in English-to-Mizo translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khenglawt-etal-2022-language">
<titleInfo>
<title>Language Resource Building and English-to-Mizo Neural Machine Translation Encountering Tonal Words</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vanlalmuansangi</namePart>
<namePart type="family">Khenglawt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahinur</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santanu</namePart>
<namePart type="family">Pal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Partha</namePart>
<namePart type="family">Pakray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ajoy</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="given">Nath</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">L.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual country like India has an enormous linguistic diversity and has an increasing demand towards developing language resources such that it will outreach in various natural language processing applications like machine translation. Low-resource language translation possesses challenges in the field of machine translation. The challenges include the availability of corpus and differences in linguistic information. This paper investigates a low-resource language pair, English-to-Mizo exploring neural machine translation by contributing an Indian language resource, i.e., English-Mizo corpus. In this work, we explore one of the main challenges to tackling tonal words existing in the Mizo language, as they add to the complexity on top of low-resource challenges for any natural language processing task. Our approach improves translation accuracy by encountering tonal words of Mizo and achieved a state-of-the-art result in English-to-Mizo translation.</abstract>
<identifier type="citekey">khenglawt-etal-2022-language</identifier>
<location>
<url>https://aclanthology.org/2022.wildre-1.9</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>48</start>
<end>54</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Resource Building and English-to-Mizo Neural Machine Translation Encountering Tonal Words
%A Khenglawt, Vanlalmuansangi
%A Laskar, Sahinur Rahman
%A Pal, Santanu
%A Pakray, Partha
%A Khan, Ajoy Kumar
%Y Jha, Girish Nath
%Y L., Sobha
%Y Bali, Kalika
%Y Ojha, Atul Kr.
%S Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F khenglawt-etal-2022-language
%X Multilingual country like India has an enormous linguistic diversity and has an increasing demand towards developing language resources such that it will outreach in various natural language processing applications like machine translation. Low-resource language translation possesses challenges in the field of machine translation. The challenges include the availability of corpus and differences in linguistic information. This paper investigates a low-resource language pair, English-to-Mizo exploring neural machine translation by contributing an Indian language resource, i.e., English-Mizo corpus. In this work, we explore one of the main challenges to tackling tonal words existing in the Mizo language, as they add to the complexity on top of low-resource challenges for any natural language processing task. Our approach improves translation accuracy by encountering tonal words of Mizo and achieved a state-of-the-art result in English-to-Mizo translation.
%U https://aclanthology.org/2022.wildre-1.9
%P 48-54
Markdown (Informal)
[Language Resource Building and English-to-Mizo Neural Machine Translation Encountering Tonal Words](https://aclanthology.org/2022.wildre-1.9) (Khenglawt et al., WILDRE 2022)
ACL