@inproceedings{durrani-etal-2016-deep,
title = "A Deep Fusion Model for Domain Adaptation in Phrase-based {MT}",
author = "Durrani, Nadir and
Sajjad, Hassan and
Joty, Shafiq and
Abdelali, Ahmed",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1299",
pages = "3177--3187",
abstract = "We present a novel fusion model for domain adaptation in Statistical Machine Translation. Our model is based on the joint source-target neural network Devlin et al., 2014, and is learned by fusing in- and out-domain models. The adaptation is performed by backpropagating errors from the output layer to the word embedding layer of each model, subsequently adjusting parameters of the composite model towards the in-domain data. On the standard tasks of translating English-to-German and Arabic-to-English TED talks, we observed average improvements of +0.9 and +0.7 BLEU points, respectively over a competition grade phrase-based system. We also demonstrate improvements over existing adaptation methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="durrani-etal-2016-deep">
<titleInfo>
<title>A Deep Fusion Model for Domain Adaptation in Phrase-based MT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nadir</namePart>
<namePart type="family">Durrani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sajjad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a novel fusion model for domain adaptation in Statistical Machine Translation. Our model is based on the joint source-target neural network Devlin et al., 2014, and is learned by fusing in- and out-domain models. The adaptation is performed by backpropagating errors from the output layer to the word embedding layer of each model, subsequently adjusting parameters of the composite model towards the in-domain data. On the standard tasks of translating English-to-German and Arabic-to-English TED talks, we observed average improvements of +0.9 and +0.7 BLEU points, respectively over a competition grade phrase-based system. We also demonstrate improvements over existing adaptation methods.</abstract>
<identifier type="citekey">durrani-etal-2016-deep</identifier>
<location>
<url>https://aclanthology.org/C16-1299</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>3177</start>
<end>3187</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Deep Fusion Model for Domain Adaptation in Phrase-based MT
%A Durrani, Nadir
%A Sajjad, Hassan
%A Joty, Shafiq
%A Abdelali, Ahmed
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F durrani-etal-2016-deep
%X We present a novel fusion model for domain adaptation in Statistical Machine Translation. Our model is based on the joint source-target neural network Devlin et al., 2014, and is learned by fusing in- and out-domain models. The adaptation is performed by backpropagating errors from the output layer to the word embedding layer of each model, subsequently adjusting parameters of the composite model towards the in-domain data. On the standard tasks of translating English-to-German and Arabic-to-English TED talks, we observed average improvements of +0.9 and +0.7 BLEU points, respectively over a competition grade phrase-based system. We also demonstrate improvements over existing adaptation methods.
%U https://aclanthology.org/C16-1299
%P 3177-3187
Markdown (Informal)
[A Deep Fusion Model for Domain Adaptation in Phrase-based MT](https://aclanthology.org/C16-1299) (Durrani et al., COLING 2016)
ACL
- Nadir Durrani, Hassan Sajjad, Shafiq Joty, and Ahmed Abdelali. 2016. A Deep Fusion Model for Domain Adaptation in Phrase-based MT. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3177–3187, Osaka, Japan. The COLING 2016 Organizing Committee.