@inproceedings{liu-etal-2023-copying,
title = "On the Copying Problem of Unsupervised {NMT}: A Training Schedule with a Language Discriminator Loss",
author = {Liu, Yihong and
Chronopoulou, Alexandra and
Sch{\"u}tze, Hinrich and
Fraser, Alexander},
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwslt-1.48",
doi = "10.18653/v1/2023.iwslt-1.48",
pages = "491--502",
abstract = "Although unsupervised neural machine translation (UNMT) has achieved success in many language pairs, the copying problem, i.e., directly copying some parts of the input sentence as the translation, is common among distant language pairs, especially when low-resource languages are involved. We find this issue is closely related to an unexpected copying behavior during online back-translation (BT). In this work, we propose a simple but effective training schedule that incorporates a language discriminator loss. The loss imposes constraints on the intermediate translation so that the translation is in the desired language. By conducting extensive experiments on different language pairs, including similar and distant, high and low-resource languages, we find that our method alleviates the copying problem, thus improving the translation performance on low-resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-copying">
<titleInfo>
<title>On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yihong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Chronopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schütze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although unsupervised neural machine translation (UNMT) has achieved success in many language pairs, the copying problem, i.e., directly copying some parts of the input sentence as the translation, is common among distant language pairs, especially when low-resource languages are involved. We find this issue is closely related to an unexpected copying behavior during online back-translation (BT). In this work, we propose a simple but effective training schedule that incorporates a language discriminator loss. The loss imposes constraints on the intermediate translation so that the translation is in the desired language. By conducting extensive experiments on different language pairs, including similar and distant, high and low-resource languages, we find that our method alleviates the copying problem, thus improving the translation performance on low-resource languages.</abstract>
<identifier type="citekey">liu-etal-2023-copying</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.48</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.48</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>491</start>
<end>502</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss
%A Liu, Yihong
%A Chronopoulou, Alexandra
%A Schütze, Hinrich
%A Fraser, Alexander
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (in-person and online)
%F liu-etal-2023-copying
%X Although unsupervised neural machine translation (UNMT) has achieved success in many language pairs, the copying problem, i.e., directly copying some parts of the input sentence as the translation, is common among distant language pairs, especially when low-resource languages are involved. We find this issue is closely related to an unexpected copying behavior during online back-translation (BT). In this work, we propose a simple but effective training schedule that incorporates a language discriminator loss. The loss imposes constraints on the intermediate translation so that the translation is in the desired language. By conducting extensive experiments on different language pairs, including similar and distant, high and low-resource languages, we find that our method alleviates the copying problem, thus improving the translation performance on low-resource languages.
%R 10.18653/v1/2023.iwslt-1.48
%U https://aclanthology.org/2023.iwslt-1.48
%U https://doi.org/10.18653/v1/2023.iwslt-1.48
%P 491-502
Markdown (Informal)
[On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss](https://aclanthology.org/2023.iwslt-1.48) (Liu et al., IWSLT 2023)
ACL