@inproceedings{briakou-carpuat-2022-synthetic,
title = "Can Synthetic Translations Improve Bitext Quality?",
author = "Briakou, Eleftheria and
Carpuat, Marine",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.326",
doi = "10.18653/v1/2022.acl-long.326",
pages = "4753--4766",
abstract = "Synthetic translations have been used for a wide range of NLP tasks primarily as a means of data augmentation. This work explores, instead, how synthetic translations can be used to revise potentially imperfect reference translations in mined bitext. We find that synthetic samples can improve bitext quality without any additional bilingual supervision when they replace the originals based on a semantic equivalence classifier that helps mitigate NMT noise. The improved quality of the revised bitext is confirmed intrinsically via human evaluation and extrinsically through bilingual induction and MT tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="briakou-carpuat-2022-synthetic">
<titleInfo>
<title>Can Synthetic Translations Improve Bitext Quality?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleftheria</namePart>
<namePart type="family">Briakou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</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">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Synthetic translations have been used for a wide range of NLP tasks primarily as a means of data augmentation. This work explores, instead, how synthetic translations can be used to revise potentially imperfect reference translations in mined bitext. We find that synthetic samples can improve bitext quality without any additional bilingual supervision when they replace the originals based on a semantic equivalence classifier that helps mitigate NMT noise. The improved quality of the revised bitext is confirmed intrinsically via human evaluation and extrinsically through bilingual induction and MT tasks.</abstract>
<identifier type="citekey">briakou-carpuat-2022-synthetic</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.326</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.326</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>4753</start>
<end>4766</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Synthetic Translations Improve Bitext Quality?
%A Briakou, Eleftheria
%A Carpuat, Marine
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F briakou-carpuat-2022-synthetic
%X Synthetic translations have been used for a wide range of NLP tasks primarily as a means of data augmentation. This work explores, instead, how synthetic translations can be used to revise potentially imperfect reference translations in mined bitext. We find that synthetic samples can improve bitext quality without any additional bilingual supervision when they replace the originals based on a semantic equivalence classifier that helps mitigate NMT noise. The improved quality of the revised bitext is confirmed intrinsically via human evaluation and extrinsically through bilingual induction and MT tasks.
%R 10.18653/v1/2022.acl-long.326
%U https://aclanthology.org/2022.acl-long.326
%U https://doi.org/10.18653/v1/2022.acl-long.326
%P 4753-4766
Markdown (Informal)
[Can Synthetic Translations Improve Bitext Quality?](https://aclanthology.org/2022.acl-long.326) (Briakou & Carpuat, ACL 2022)
ACL
- Eleftheria Briakou and Marine Carpuat. 2022. Can Synthetic Translations Improve Bitext Quality?. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4753–4766, Dublin, Ireland. Association for Computational Linguistics.