@inproceedings{wei-etal-2020-iterative,
title = "Iterative Domain-Repaired Back-Translation",
author = "Wei, Hao-Ran and
Zhang, Zhirui and
Chen, Boxing and
Luo, Weihua",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.474",
doi = "10.18653/v1/2020.emnlp-main.474",
pages = "5884--5893",
abstract = "In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent. One common and effective strategy for this case is exploiting in-domain monolingual data with the back-translation method. However, the synthetic parallel data is very noisy because they are generated by imperfect out-of-domain systems, resulting in the poor performance of domain adaptation. To address this issue, we propose a novel iterative domain-repaired back-translation framework, which introduces the Domain-Repair (DR) model to refine translations in synthetic bilingual data. To this end, we construct corresponding data for the DR model training by round-trip translating the monolingual sentences, and then design the unified training framework to optimize paired DR and NMT models jointly. Experiments on adapting NMT models between specific domains and from the general domain to specific domains demonstrate the effectiveness of our proposed approach, achieving 15.79 and 4.47 BLEU improvements on average over unadapted models and back-translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2020-iterative">
<titleInfo>
<title>Iterative Domain-Repaired Back-Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao-Ran</namePart>
<namePart type="family">Wei</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">Boxing</namePart>
<namePart type="family">Chen</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>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent. One common and effective strategy for this case is exploiting in-domain monolingual data with the back-translation method. However, the synthetic parallel data is very noisy because they are generated by imperfect out-of-domain systems, resulting in the poor performance of domain adaptation. To address this issue, we propose a novel iterative domain-repaired back-translation framework, which introduces the Domain-Repair (DR) model to refine translations in synthetic bilingual data. To this end, we construct corresponding data for the DR model training by round-trip translating the monolingual sentences, and then design the unified training framework to optimize paired DR and NMT models jointly. Experiments on adapting NMT models between specific domains and from the general domain to specific domains demonstrate the effectiveness of our proposed approach, achieving 15.79 and 4.47 BLEU improvements on average over unadapted models and back-translation.</abstract>
<identifier type="citekey">wei-etal-2020-iterative</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.474</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.474</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>5884</start>
<end>5893</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Iterative Domain-Repaired Back-Translation
%A Wei, Hao-Ran
%A Zhang, Zhirui
%A Chen, Boxing
%A Luo, Weihua
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F wei-etal-2020-iterative
%X In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent. One common and effective strategy for this case is exploiting in-domain monolingual data with the back-translation method. However, the synthetic parallel data is very noisy because they are generated by imperfect out-of-domain systems, resulting in the poor performance of domain adaptation. To address this issue, we propose a novel iterative domain-repaired back-translation framework, which introduces the Domain-Repair (DR) model to refine translations in synthetic bilingual data. To this end, we construct corresponding data for the DR model training by round-trip translating the monolingual sentences, and then design the unified training framework to optimize paired DR and NMT models jointly. Experiments on adapting NMT models between specific domains and from the general domain to specific domains demonstrate the effectiveness of our proposed approach, achieving 15.79 and 4.47 BLEU improvements on average over unadapted models and back-translation.
%R 10.18653/v1/2020.emnlp-main.474
%U https://aclanthology.org/2020.emnlp-main.474
%U https://doi.org/10.18653/v1/2020.emnlp-main.474
%P 5884-5893
Markdown (Informal)
[Iterative Domain-Repaired Back-Translation](https://aclanthology.org/2020.emnlp-main.474) (Wei et al., EMNLP 2020)
ACL
- Hao-Ran Wei, Zhirui Zhang, Boxing Chen, and Weihua Luo. 2020. Iterative Domain-Repaired Back-Translation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5884–5893, Online. Association for Computational Linguistics.