@inproceedings{espla-gomis-etal-2022-cross,
title = "Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translation",
author = "Espl{\`a}-Gomis, Miquel and
S{\'a}nchez-Cartagena, V{\'\i}ctor M. and
P{\'e}rez-Ortiz, Juan Antonio and
S{\'a}nchez-Mart{\'\i}nez, Felipe",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.511",
doi = "10.18653/v1/2022.emnlp-main.511",
pages = "7532--7543",
abstract = "Computer-aided translation (CAT) tools based on translation memories (MT) play a prominent role in the translation workflow of professional translators. However, the reduced availability of in-domain TMs, as compared to in-domain monolingual corpora, limits its adoption for a number of translation tasks. In this paper, we introduce a novel neural approach aimed at overcoming this limitation by exploiting not only TMs, but also in-domain target-language (TL) monolingual corpora, and still enabling a similar functionality to that offered by conventional TM-based CAT tools. Our approach relies on cross-lingual sentence embeddings to retrieve translation proposals from TL monolingual corpora, and on a neural model to estimate their post-editing effort. The paper presents an automatic evaluation of these techniques on four language pairs that shows that our approach can successfully exploit monolingual texts in a TM-based CAT environment, increasing the amount of useful translation proposals, and that our neural model for estimating the post-editing effort enables the combination of translation proposals obtained from monolingual corpora and from TMs in the usual way. A human evaluation performed on a single language pair confirms the results of the automatic evaluation and seems to indicate that the translation proposals retrieved with our approach are more useful than what the automatic evaluation shows.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="espla-gomis-etal-2022-cross">
<titleInfo>
<title>Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Víctor</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Sánchez-Cartagena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Pérez-Ortiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Sánchez-Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Computer-aided translation (CAT) tools based on translation memories (MT) play a prominent role in the translation workflow of professional translators. However, the reduced availability of in-domain TMs, as compared to in-domain monolingual corpora, limits its adoption for a number of translation tasks. In this paper, we introduce a novel neural approach aimed at overcoming this limitation by exploiting not only TMs, but also in-domain target-language (TL) monolingual corpora, and still enabling a similar functionality to that offered by conventional TM-based CAT tools. Our approach relies on cross-lingual sentence embeddings to retrieve translation proposals from TL monolingual corpora, and on a neural model to estimate their post-editing effort. The paper presents an automatic evaluation of these techniques on four language pairs that shows that our approach can successfully exploit monolingual texts in a TM-based CAT environment, increasing the amount of useful translation proposals, and that our neural model for estimating the post-editing effort enables the combination of translation proposals obtained from monolingual corpora and from TMs in the usual way. A human evaluation performed on a single language pair confirms the results of the automatic evaluation and seems to indicate that the translation proposals retrieved with our approach are more useful than what the automatic evaluation shows.</abstract>
<identifier type="citekey">espla-gomis-etal-2022-cross</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.511</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.511</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7532</start>
<end>7543</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translation
%A Esplà-Gomis, Miquel
%A Sánchez-Cartagena, Víctor M.
%A Pérez-Ortiz, Juan Antonio
%A Sánchez-Martínez, Felipe
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F espla-gomis-etal-2022-cross
%X Computer-aided translation (CAT) tools based on translation memories (MT) play a prominent role in the translation workflow of professional translators. However, the reduced availability of in-domain TMs, as compared to in-domain monolingual corpora, limits its adoption for a number of translation tasks. In this paper, we introduce a novel neural approach aimed at overcoming this limitation by exploiting not only TMs, but also in-domain target-language (TL) monolingual corpora, and still enabling a similar functionality to that offered by conventional TM-based CAT tools. Our approach relies on cross-lingual sentence embeddings to retrieve translation proposals from TL monolingual corpora, and on a neural model to estimate their post-editing effort. The paper presents an automatic evaluation of these techniques on four language pairs that shows that our approach can successfully exploit monolingual texts in a TM-based CAT environment, increasing the amount of useful translation proposals, and that our neural model for estimating the post-editing effort enables the combination of translation proposals obtained from monolingual corpora and from TMs in the usual way. A human evaluation performed on a single language pair confirms the results of the automatic evaluation and seems to indicate that the translation proposals retrieved with our approach are more useful than what the automatic evaluation shows.
%R 10.18653/v1/2022.emnlp-main.511
%U https://aclanthology.org/2022.emnlp-main.511
%U https://doi.org/10.18653/v1/2022.emnlp-main.511
%P 7532-7543
Markdown (Informal)
[Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translation](https://aclanthology.org/2022.emnlp-main.511) (Esplà-Gomis et al., EMNLP 2022)
ACL