@inproceedings{chen-etal-2016-bilingual,
title = "Bilingual Methods for Adaptive Training Data Selection for Machine Translation",
author = "Chen, Boxing and
Kuhn, Roland and
Foster, George and
Cherry, Colin and
Huang, Fei",
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.8",
pages = "93--106",
abstract = "In this paper, we propose a new data selection method which uses semi-supervised convolutional neural networks based on bitokens (Bi-SSCNNs) for training machine translation systems from a large bilingual corpus. In earlier work, we devised a data selection method based on semi-supervised convolutional neural networks (SSCNNs). The new method, Bi-SSCNN, is based on bitokens, which use bilingual information. When the new methods are tested on two translation tasks (Chinese-to-English and Arabic-to-English), they significantly outperform the other three data selection methods in the experiments. We also show that the BiSSCNN method is much more effective than other methods in preventing noisy sentence pairs from being chosen for training. More interestingly, this method only needs a tiny amount of in-domain data to train the selection model, which makes fine-grained topic-dependent translation adaptation possible. In the follow-up experiments, we find that neural machine translation (NMT) is more sensitive to noisy data than statistical machine translation (SMT). Therefore, Bi-SSCNN which can effectively screen out noisy sentence pairs, can benefit NMT much more than SMT.We observed a BLEU improvement over 3 points on an English-to-French WMT task when Bi-SSCNNs were used.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2016-bilingual">
<titleInfo>
<title>Bilingual Methods for Adaptive Training Data Selection for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boxing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roland</namePart>
<namePart type="family">Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</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>In this paper, we propose a new data selection method which uses semi-supervised convolutional neural networks based on bitokens (Bi-SSCNNs) for training machine translation systems from a large bilingual corpus. In earlier work, we devised a data selection method based on semi-supervised convolutional neural networks (SSCNNs). The new method, Bi-SSCNN, is based on bitokens, which use bilingual information. When the new methods are tested on two translation tasks (Chinese-to-English and Arabic-to-English), they significantly outperform the other three data selection methods in the experiments. We also show that the BiSSCNN method is much more effective than other methods in preventing noisy sentence pairs from being chosen for training. More interestingly, this method only needs a tiny amount of in-domain data to train the selection model, which makes fine-grained topic-dependent translation adaptation possible. In the follow-up experiments, we find that neural machine translation (NMT) is more sensitive to noisy data than statistical machine translation (SMT). Therefore, Bi-SSCNN which can effectively screen out noisy sentence pairs, can benefit NMT much more than SMT.We observed a BLEU improvement over 3 points on an English-to-French WMT task when Bi-SSCNNs were used.</abstract>
<identifier type="citekey">chen-etal-2016-bilingual</identifier>
<location>
<url>https://aclanthology.org/2016.amta-researchers.8</url>
</location>
<part>
<date>2016-oct 28 - nov 1</date>
<extent unit="page">
<start>93</start>
<end>106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Methods for Adaptive Training Data Selection for Machine Translation
%A Chen, Boxing
%A Kuhn, Roland
%A Foster, George
%A Cherry, Colin
%A Huang, Fei
%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 chen-etal-2016-bilingual
%X In this paper, we propose a new data selection method which uses semi-supervised convolutional neural networks based on bitokens (Bi-SSCNNs) for training machine translation systems from a large bilingual corpus. In earlier work, we devised a data selection method based on semi-supervised convolutional neural networks (SSCNNs). The new method, Bi-SSCNN, is based on bitokens, which use bilingual information. When the new methods are tested on two translation tasks (Chinese-to-English and Arabic-to-English), they significantly outperform the other three data selection methods in the experiments. We also show that the BiSSCNN method is much more effective than other methods in preventing noisy sentence pairs from being chosen for training. More interestingly, this method only needs a tiny amount of in-domain data to train the selection model, which makes fine-grained topic-dependent translation adaptation possible. In the follow-up experiments, we find that neural machine translation (NMT) is more sensitive to noisy data than statistical machine translation (SMT). Therefore, Bi-SSCNN which can effectively screen out noisy sentence pairs, can benefit NMT much more than SMT.We observed a BLEU improvement over 3 points on an English-to-French WMT task when Bi-SSCNNs were used.
%U https://aclanthology.org/2016.amta-researchers.8
%P 93-106
Markdown (Informal)
[Bilingual Methods for Adaptive Training Data Selection for Machine Translation](https://aclanthology.org/2016.amta-researchers.8) (Chen et al., AMTA 2016)
ACL