@inproceedings{mansour-etal-2014-automatic,
title = "Automatic dialect classification for statistical machine translation",
author = "Mansour, Saab and
Al-Onaizan, Yaser and
Blackwood, Graeme and
Tillmann, Christoph",
editor = "Al-Onaizan, Yaser and
Simard, Michel",
booktitle = "Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track",
month = oct # " 22-26",
year = "2014",
address = "Vancouver, Canada",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2014.amta-researchers.26",
pages = "342--355",
abstract = "The training data for statistical machine translation are gathered from various sources representing a mixture of domains. In this work, we argue that when translating dialects representing varieties of the same language, a manually assigned data source is not a reliable indicator of the dialect. We resort to automatic dialect classification to refine the training corpora according to the different dialects and build improved dialect specific systems. A fairly standard classifier for Arabic developed within this work achieves state-of-the-art performance, with classification precision above 90{\%}, making it usefully accurate for our application. The classification of the data is then used to distinguish between the different dialects, split the data accordingly, and utilize the new splits for several adaptation techniques. Performing translation experiments on a large scale dialectal Arabic to English translation task, our results show that the classifier generates better contrast between the dialects and achieves superior translation quality than using the original manual corpora splits.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mansour-etal-2014-automatic">
<titleInfo>
<title>Automatic dialect classification for statistical machine translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saab</namePart>
<namePart type="family">Mansour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graeme</namePart>
<namePart type="family">Blackwood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Tillmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-oct 22-26</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Simard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The training data for statistical machine translation are gathered from various sources representing a mixture of domains. In this work, we argue that when translating dialects representing varieties of the same language, a manually assigned data source is not a reliable indicator of the dialect. We resort to automatic dialect classification to refine the training corpora according to the different dialects and build improved dialect specific systems. A fairly standard classifier for Arabic developed within this work achieves state-of-the-art performance, with classification precision above 90%, making it usefully accurate for our application. The classification of the data is then used to distinguish between the different dialects, split the data accordingly, and utilize the new splits for several adaptation techniques. Performing translation experiments on a large scale dialectal Arabic to English translation task, our results show that the classifier generates better contrast between the dialects and achieves superior translation quality than using the original manual corpora splits.</abstract>
<identifier type="citekey">mansour-etal-2014-automatic</identifier>
<location>
<url>https://aclanthology.org/2014.amta-researchers.26</url>
</location>
<part>
<date>2014-oct 22-26</date>
<extent unit="page">
<start>342</start>
<end>355</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic dialect classification for statistical machine translation
%A Mansour, Saab
%A Al-Onaizan, Yaser
%A Blackwood, Graeme
%A Tillmann, Christoph
%Y Al-Onaizan, Yaser
%Y Simard, Michel
%S Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track
%D 2014
%8 oct 22 26
%I Association for Machine Translation in the Americas
%C Vancouver, Canada
%F mansour-etal-2014-automatic
%X The training data for statistical machine translation are gathered from various sources representing a mixture of domains. In this work, we argue that when translating dialects representing varieties of the same language, a manually assigned data source is not a reliable indicator of the dialect. We resort to automatic dialect classification to refine the training corpora according to the different dialects and build improved dialect specific systems. A fairly standard classifier for Arabic developed within this work achieves state-of-the-art performance, with classification precision above 90%, making it usefully accurate for our application. The classification of the data is then used to distinguish between the different dialects, split the data accordingly, and utilize the new splits for several adaptation techniques. Performing translation experiments on a large scale dialectal Arabic to English translation task, our results show that the classifier generates better contrast between the dialects and achieves superior translation quality than using the original manual corpora splits.
%U https://aclanthology.org/2014.amta-researchers.26
%P 342-355
Markdown (Informal)
[Automatic dialect classification for statistical machine translation](https://aclanthology.org/2014.amta-researchers.26) (Mansour et al., AMTA 2014)
ACL
- Saab Mansour, Yaser Al-Onaizan, Graeme Blackwood, and Christoph Tillmann. 2014. Automatic dialect classification for statistical machine translation. In Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track, pages 342–355, Vancouver, Canada. Association for Machine Translation in the Americas.