@inproceedings{shi-etal-2019-improving,
title = "Improving Neural Machine Translation by Achieving Knowledge Transfer with Sentence Alignment Learning",
author = "Shi, Xuewen and
Huang, Heyan and
Wang, Wenguan and
Jian, Ping and
Tang, Yi-Kun",
editor = "Bansal, Mohit and
Villavicencio, Aline",
booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K19-1025",
doi = "10.18653/v1/K19-1025",
pages = "260--270",
abstract = "Neural Machine Translation (NMT) optimized by Maximum Likelihood Estimation (MLE) lacks the guarantee of translation adequacy. To alleviate this problem, we propose an NMT approach that heightens the adequacy in machine translation by transferring the semantic knowledge learned from bilingual sentence alignment. Specifically, we first design a discriminator that learns to estimate sentence aligning score over translation candidates, and then the learned semantic knowledge is transfered to the NMT model under an adversarial learning framework. We also propose a gated self-attention based encoder for sentence embedding. Furthermore, an N-pair training loss is introduced in our framework to aid the discriminator in better capturing lexical evidence in translation candidates. Experimental results show that our proposed method outperforms baseline NMT models on Chinese-to-English and English-to-German translation tasks. Further analysis also indicates the detailed semantic knowledge transfered from the discriminator to the NMT model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2019-improving">
<titleInfo>
<title>Improving Neural Machine Translation by Achieving Knowledge Transfer with Sentence Alignment Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuewen</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heyan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenguan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Jian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Kun</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Machine Translation (NMT) optimized by Maximum Likelihood Estimation (MLE) lacks the guarantee of translation adequacy. To alleviate this problem, we propose an NMT approach that heightens the adequacy in machine translation by transferring the semantic knowledge learned from bilingual sentence alignment. Specifically, we first design a discriminator that learns to estimate sentence aligning score over translation candidates, and then the learned semantic knowledge is transfered to the NMT model under an adversarial learning framework. We also propose a gated self-attention based encoder for sentence embedding. Furthermore, an N-pair training loss is introduced in our framework to aid the discriminator in better capturing lexical evidence in translation candidates. Experimental results show that our proposed method outperforms baseline NMT models on Chinese-to-English and English-to-German translation tasks. Further analysis also indicates the detailed semantic knowledge transfered from the discriminator to the NMT model.</abstract>
<identifier type="citekey">shi-etal-2019-improving</identifier>
<identifier type="doi">10.18653/v1/K19-1025</identifier>
<location>
<url>https://aclanthology.org/K19-1025</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>260</start>
<end>270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Neural Machine Translation by Achieving Knowledge Transfer with Sentence Alignment Learning
%A Shi, Xuewen
%A Huang, Heyan
%A Wang, Wenguan
%A Jian, Ping
%A Tang, Yi-Kun
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F shi-etal-2019-improving
%X Neural Machine Translation (NMT) optimized by Maximum Likelihood Estimation (MLE) lacks the guarantee of translation adequacy. To alleviate this problem, we propose an NMT approach that heightens the adequacy in machine translation by transferring the semantic knowledge learned from bilingual sentence alignment. Specifically, we first design a discriminator that learns to estimate sentence aligning score over translation candidates, and then the learned semantic knowledge is transfered to the NMT model under an adversarial learning framework. We also propose a gated self-attention based encoder for sentence embedding. Furthermore, an N-pair training loss is introduced in our framework to aid the discriminator in better capturing lexical evidence in translation candidates. Experimental results show that our proposed method outperforms baseline NMT models on Chinese-to-English and English-to-German translation tasks. Further analysis also indicates the detailed semantic knowledge transfered from the discriminator to the NMT model.
%R 10.18653/v1/K19-1025
%U https://aclanthology.org/K19-1025
%U https://doi.org/10.18653/v1/K19-1025
%P 260-270
Markdown (Informal)
[Improving Neural Machine Translation by Achieving Knowledge Transfer with Sentence Alignment Learning](https://aclanthology.org/K19-1025) (Shi et al., CoNLL 2019)
ACL