@inproceedings{weng-etal-2017-neural,
title = "Neural Machine Translation with Word Predictions",
author = "Weng, Rongxiang and
Huang, Shujian and
Zheng, Zaixiang and
Dai, Xinyu and
Chen, Jiajun",
editor = "Palmer, Martha and
Hwa, Rebecca and
Riedel, Sebastian",
booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D17-1013",
doi = "10.18653/v1/D17-1013",
pages = "136--145",
abstract = "In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence. These vectors are generated by parameters which are updated by back-propagation of translation errors through time. We argue that propagating errors through the end-to-end recurrent structures are not a direct way of control the hidden vectors. In this paper, we propose to use word predictions as a mechanism for direct supervision. More specifically, we require these vectors to be able to predict the vocabulary in target sentence. Our simple mechanism ensures better representations in the encoder and decoder without using any extra data or annotation. It is also helpful in reducing the target side vocabulary and improving the decoding efficiency. Experiments on Chinese-English machine translation task show an average BLEU improvement by 4.53, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weng-etal-2017-neural">
<titleInfo>
<title>Neural Machine Translation with Word Predictions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rongxiang</namePart>
<namePart type="family">Weng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shujian</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaixiang</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence. These vectors are generated by parameters which are updated by back-propagation of translation errors through time. We argue that propagating errors through the end-to-end recurrent structures are not a direct way of control the hidden vectors. In this paper, we propose to use word predictions as a mechanism for direct supervision. More specifically, we require these vectors to be able to predict the vocabulary in target sentence. Our simple mechanism ensures better representations in the encoder and decoder without using any extra data or annotation. It is also helpful in reducing the target side vocabulary and improving the decoding efficiency. Experiments on Chinese-English machine translation task show an average BLEU improvement by 4.53, respectively.</abstract>
<identifier type="citekey">weng-etal-2017-neural</identifier>
<identifier type="doi">10.18653/v1/D17-1013</identifier>
<location>
<url>https://aclanthology.org/D17-1013</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>136</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Machine Translation with Word Predictions
%A Weng, Rongxiang
%A Huang, Shujian
%A Zheng, Zaixiang
%A Dai, Xinyu
%A Chen, Jiajun
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F weng-etal-2017-neural
%X In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence. These vectors are generated by parameters which are updated by back-propagation of translation errors through time. We argue that propagating errors through the end-to-end recurrent structures are not a direct way of control the hidden vectors. In this paper, we propose to use word predictions as a mechanism for direct supervision. More specifically, we require these vectors to be able to predict the vocabulary in target sentence. Our simple mechanism ensures better representations in the encoder and decoder without using any extra data or annotation. It is also helpful in reducing the target side vocabulary and improving the decoding efficiency. Experiments on Chinese-English machine translation task show an average BLEU improvement by 4.53, respectively.
%R 10.18653/v1/D17-1013
%U https://aclanthology.org/D17-1013
%U https://doi.org/10.18653/v1/D17-1013
%P 136-145
Markdown (Informal)
[Neural Machine Translation with Word Predictions](https://aclanthology.org/D17-1013) (Weng et al., EMNLP 2017)
ACL
- Rongxiang Weng, Shujian Huang, Zaixiang Zheng, Xinyu Dai, and Jiajun Chen. 2017. Neural Machine Translation with Word Predictions. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 136–145, Copenhagen, Denmark. Association for Computational Linguistics.