@inproceedings{imamura-sumita-2016-multi,
title = "Multi-domain Adaptation for Statistical Machine Translation Based on Feature Augmentation",
author = "Imamura, Kenji and
Sumita, Eiichiro",
editor = "Green, Spence and
Schwartz, Lane",
booktitle = "Conferences of the Association for Machine Translation in the Americas: MT Researchers' Track",
month = oct # " 28 - " # nov # " 1",
year = "2016",
address = "Austin, TX, USA",
publisher = "The Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2016.amta-researchers.7",
pages = "79--92",
abstract = "Domain adaptation is a major challenge when applying machine translation to practical tasks. In this paper, we present domain adaptation methods for machine translation that assume multiple domains. The proposed methods combine two model types: a corpus-concatenated model covering multiple domains and single-domain models that are accurate but sparse in specific domains. We combine the advantages of both models using feature augmentation for domain adaptation in machine learning. Our experimental results show that the BLEU scores of the proposed method clearly surpass those of single-domain models for low-resource domains. For high-resource domains, the scores of the proposed method were superior to those of both single-domain and corpusconcatenated models. Even in domains having a million bilingual sentences, the translation quality was at least preserved and even improved in some domains. These results demonstrate that state-of-the-art domain adaptation can be realized with appropriate settings, even when using standard log-linear models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="imamura-sumita-2016-multi">
<titleInfo>
<title>Multi-domain Adaptation for Statistical Machine Translation Based on Feature Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Imamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-oct 28 - nov 1</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Conferences of the Association for Machine Translation in the Americas: MT Researchers’ Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Spence</namePart>
<namePart type="family">Green</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Austin, TX, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Domain adaptation is a major challenge when applying machine translation to practical tasks. In this paper, we present domain adaptation methods for machine translation that assume multiple domains. The proposed methods combine two model types: a corpus-concatenated model covering multiple domains and single-domain models that are accurate but sparse in specific domains. We combine the advantages of both models using feature augmentation for domain adaptation in machine learning. Our experimental results show that the BLEU scores of the proposed method clearly surpass those of single-domain models for low-resource domains. For high-resource domains, the scores of the proposed method were superior to those of both single-domain and corpusconcatenated models. Even in domains having a million bilingual sentences, the translation quality was at least preserved and even improved in some domains. These results demonstrate that state-of-the-art domain adaptation can be realized with appropriate settings, even when using standard log-linear models.</abstract>
<identifier type="citekey">imamura-sumita-2016-multi</identifier>
<location>
<url>https://aclanthology.org/2016.amta-researchers.7</url>
</location>
<part>
<date>2016-oct 28 - nov 1</date>
<extent unit="page">
<start>79</start>
<end>92</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-domain Adaptation for Statistical Machine Translation Based on Feature Augmentation
%A Imamura, Kenji
%A Sumita, Eiichiro
%Y Green, Spence
%Y Schwartz, Lane
%S Conferences of the Association for Machine Translation in the Americas: MT Researchers’ Track
%D 2016
%8 oct 28 nov 1
%I The Association for Machine Translation in the Americas
%C Austin, TX, USA
%F imamura-sumita-2016-multi
%X Domain adaptation is a major challenge when applying machine translation to practical tasks. In this paper, we present domain adaptation methods for machine translation that assume multiple domains. The proposed methods combine two model types: a corpus-concatenated model covering multiple domains and single-domain models that are accurate but sparse in specific domains. We combine the advantages of both models using feature augmentation for domain adaptation in machine learning. Our experimental results show that the BLEU scores of the proposed method clearly surpass those of single-domain models for low-resource domains. For high-resource domains, the scores of the proposed method were superior to those of both single-domain and corpusconcatenated models. Even in domains having a million bilingual sentences, the translation quality was at least preserved and even improved in some domains. These results demonstrate that state-of-the-art domain adaptation can be realized with appropriate settings, even when using standard log-linear models.
%U https://aclanthology.org/2016.amta-researchers.7
%P 79-92
Markdown (Informal)
[Multi-domain Adaptation for Statistical Machine Translation Based on Feature Augmentation](https://aclanthology.org/2016.amta-researchers.7) (Imamura & Sumita, AMTA 2016)
ACL