@inproceedings{lewis-yang-2012-building,
title = "Building {MT} for a Severely Under-Resourced Language: White {H}mong",
author = "Lewis, William and
Yang, Phong",
booktitle = "Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers",
month = oct # " 28-" # nov # " 1",
year = "2012",
address = "San Diego, California, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2012.amta-papers.10",
abstract = "In this paper, we discuss the development of statistical machine translation for English to/from White Hmong (Language code: mww). White Hmong is a Hmong-Mien language, originally spoken mostly in Southeast Asia, but now predominantly spoken by a large diaspora throughout the world, with populations in the United States, Australia, France, Thailand and elsewhere. Building statistical translation systems for Hmong proved to be incredibly challenging since there are no known parallel or monolingual corpora for the language; in fact, finding data for Hmong proved to be one of the biggest challenges to getting the project off the ground. It was only through a close collaboration with the Hmong community, and active and tireless participation of Hmong speakers, that it became possible to build up a critical mass of data to make the translation project a reality. We see this effort as potentially replicable for other severely resource poor languages of the world, which is likely the case for the majority of the languages still spoken on the planet. Further, the work here suggests that research and work on other severely under-resourced languages can have significant positive impacts for the affected communities, both for accessibility and language preservation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lewis-yang-2012-building">
<titleInfo>
<title>Building MT for a Severely Under-Resourced Language: White Hmong</title>
</titleInfo>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-oct 28-nov 1</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we discuss the development of statistical machine translation for English to/from White Hmong (Language code: mww). White Hmong is a Hmong-Mien language, originally spoken mostly in Southeast Asia, but now predominantly spoken by a large diaspora throughout the world, with populations in the United States, Australia, France, Thailand and elsewhere. Building statistical translation systems for Hmong proved to be incredibly challenging since there are no known parallel or monolingual corpora for the language; in fact, finding data for Hmong proved to be one of the biggest challenges to getting the project off the ground. It was only through a close collaboration with the Hmong community, and active and tireless participation of Hmong speakers, that it became possible to build up a critical mass of data to make the translation project a reality. We see this effort as potentially replicable for other severely resource poor languages of the world, which is likely the case for the majority of the languages still spoken on the planet. Further, the work here suggests that research and work on other severely under-resourced languages can have significant positive impacts for the affected communities, both for accessibility and language preservation.</abstract>
<identifier type="citekey">lewis-yang-2012-building</identifier>
<location>
<url>https://aclanthology.org/2012.amta-papers.10</url>
</location>
<part>
<date>2012-oct 28-nov 1</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building MT for a Severely Under-Resourced Language: White Hmong
%A Lewis, William
%A Yang, Phong
%S Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers
%D 2012
%8 oct 28 nov 1
%I Association for Machine Translation in the Americas
%C San Diego, California, USA
%F lewis-yang-2012-building
%X In this paper, we discuss the development of statistical machine translation for English to/from White Hmong (Language code: mww). White Hmong is a Hmong-Mien language, originally spoken mostly in Southeast Asia, but now predominantly spoken by a large diaspora throughout the world, with populations in the United States, Australia, France, Thailand and elsewhere. Building statistical translation systems for Hmong proved to be incredibly challenging since there are no known parallel or monolingual corpora for the language; in fact, finding data for Hmong proved to be one of the biggest challenges to getting the project off the ground. It was only through a close collaboration with the Hmong community, and active and tireless participation of Hmong speakers, that it became possible to build up a critical mass of data to make the translation project a reality. We see this effort as potentially replicable for other severely resource poor languages of the world, which is likely the case for the majority of the languages still spoken on the planet. Further, the work here suggests that research and work on other severely under-resourced languages can have significant positive impacts for the affected communities, both for accessibility and language preservation.
%U https://aclanthology.org/2012.amta-papers.10
Markdown (Informal)
[Building MT for a Severely Under-Resourced Language: White Hmong](https://aclanthology.org/2012.amta-papers.10) (Lewis & Yang, AMTA 2012)
ACL