@inproceedings{wang-etal-2021-rethinking-zero,
title = "Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables",
author = "Wang, Weizhi and
Zhang, Zhirui and
Du, Yichao and
Chen, Boxing and
Xie, Jun and
Luo, Weihua",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.366",
doi = "10.18653/v1/2021.findings-emnlp.366",
pages = "4321--4327",
abstract = "Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the output language and language invariant semantics due to the maximum likelihood training objective, leading to poor transfer performance on zero-shot translation. In this paper, we introduce a denoising autoencoder objective based on pivot language into traditional training objective to improve the translation accuracy on zero-shot directions. The theoretical analysis from the perspective of latent variables shows that our approach actually implicitly maximizes the probability distributions for zero-shot directions. On two benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively eliminate the spurious correlations and significantly outperforms state-of-the-art methods with a remarkable performance. Our code is available at \url{https://github.com/Victorwz/zs-nmt-dae}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-rethinking-zero">
<titleInfo>
<title>Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weizhi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhirui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Jun</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weihua</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the output language and language invariant semantics due to the maximum likelihood training objective, leading to poor transfer performance on zero-shot translation. In this paper, we introduce a denoising autoencoder objective based on pivot language into traditional training objective to improve the translation accuracy on zero-shot directions. The theoretical analysis from the perspective of latent variables shows that our approach actually implicitly maximizes the probability distributions for zero-shot directions. On two benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively eliminate the spurious correlations and significantly outperforms state-of-the-art methods with a remarkable performance. Our code is available at https://github.com/Victorwz/zs-nmt-dae.</abstract>
<identifier type="citekey">wang-etal-2021-rethinking-zero</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.366</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.366</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4321</start>
<end>4327</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables
%A Wang, Weizhi
%A Zhang, Zhirui
%A Du, Yichao
%A Chen, Boxing
%A Xie, Jun
%A Luo, Weihua
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F wang-etal-2021-rethinking-zero
%X Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the output language and language invariant semantics due to the maximum likelihood training objective, leading to poor transfer performance on zero-shot translation. In this paper, we introduce a denoising autoencoder objective based on pivot language into traditional training objective to improve the translation accuracy on zero-shot directions. The theoretical analysis from the perspective of latent variables shows that our approach actually implicitly maximizes the probability distributions for zero-shot directions. On two benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively eliminate the spurious correlations and significantly outperforms state-of-the-art methods with a remarkable performance. Our code is available at https://github.com/Victorwz/zs-nmt-dae.
%R 10.18653/v1/2021.findings-emnlp.366
%U https://aclanthology.org/2021.findings-emnlp.366
%U https://doi.org/10.18653/v1/2021.findings-emnlp.366
%P 4321-4327
Markdown (Informal)
[Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables](https://aclanthology.org/2021.findings-emnlp.366) (Wang et al., Findings 2021)
ACL