@inproceedings{sharami-etal-2023-tailoring,
title = "Tailoring Domain Adaptation for Machine Translation Quality Estimation",
author = "Sharami, Javad Pourmostafa Roshan and
Shterionov, Dimitar and
Blain, Fr{\'e}d{\'e}ric and
Vanmassenhove, Eva and
Sisto, Mirella De and
Emmery, Chris and
Spronck, Pieter",
editor = "Nurminen, Mary and
Brenner, Judith and
Koponen, Maarit and
Latomaa, Sirkku and
Mikhailov, Mikhail and
Schierl, Frederike and
Ranasinghe, Tharindu and
Vanmassenhove, Eva and
Vidal, Sergi Alvarez and
Aranberri, Nora and
Nunziatini, Mara and
Escart{\'\i}n, Carla Parra and
Forcada, Mikel and
Popovic, Maja and
Scarton, Carolina and
Moniz, Helena",
booktitle = "Proceedings of the 24th Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2023",
address = "Tampere, Finland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2023.eamt-1.2",
pages = "9--20",
abstract = "While quality estimation (QE) can play an important role in the translation process, its effectiveness relies on the availability and quality of training data. For QE in particular, high-quality labeled data is often lacking due to the high-cost and effort associated with labeling such data. Aside from the data scarcity challenge, QE models should also be generalizabile, i.e., they should be able to handle data from different domains, both generic and specific. To alleviate these two main issues {---} data scarcity and domain mismatch {---} this paper combines domain adaptation and data augmentation within a robust QE system. Our method is to first train a generic QE model and then fine-tune it on a specific domain while retaining generic knowledge. Our results show a significant improvement for all the language pairs investigated, better cross-lingual inference, and a superior performance in zero-shot learning scenarios as compared to state-of-the-art baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharami-etal-2023-tailoring">
<titleInfo>
<title>Tailoring Domain Adaptation for Machine Translation Quality Estimation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Javad</namePart>
<namePart type="given">Pourmostafa</namePart>
<namePart type="given">Roshan</namePart>
<namePart type="family">Sharami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Shterionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Blain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="given">De</namePart>
<namePart type="family">Sisto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Emmery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pieter</namePart>
<namePart type="family">Spronck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Brenner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirkku</namePart>
<namePart type="family">Latomaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederike</namePart>
<namePart type="family">Schierl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="given">Alvarez</namePart>
<namePart type="family">Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Nunziatini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tampere, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While quality estimation (QE) can play an important role in the translation process, its effectiveness relies on the availability and quality of training data. For QE in particular, high-quality labeled data is often lacking due to the high-cost and effort associated with labeling such data. Aside from the data scarcity challenge, QE models should also be generalizabile, i.e., they should be able to handle data from different domains, both generic and specific. To alleviate these two main issues — data scarcity and domain mismatch — this paper combines domain adaptation and data augmentation within a robust QE system. Our method is to first train a generic QE model and then fine-tune it on a specific domain while retaining generic knowledge. Our results show a significant improvement for all the language pairs investigated, better cross-lingual inference, and a superior performance in zero-shot learning scenarios as compared to state-of-the-art baselines.</abstract>
<identifier type="citekey">sharami-etal-2023-tailoring</identifier>
<location>
<url>https://aclanthology.org/2023.eamt-1.2</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>9</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tailoring Domain Adaptation for Machine Translation Quality Estimation
%A Sharami, Javad Pourmostafa Roshan
%A Shterionov, Dimitar
%A Blain, Frédéric
%A Vanmassenhove, Eva
%A Sisto, Mirella De
%A Emmery, Chris
%A Spronck, Pieter
%Y Nurminen, Mary
%Y Brenner, Judith
%Y Koponen, Maarit
%Y Latomaa, Sirkku
%Y Mikhailov, Mikhail
%Y Schierl, Frederike
%Y Ranasinghe, Tharindu
%Y Vanmassenhove, Eva
%Y Vidal, Sergi Alvarez
%Y Aranberri, Nora
%Y Nunziatini, Mara
%Y Escartín, Carla Parra
%Y Forcada, Mikel
%Y Popovic, Maja
%Y Scarton, Carolina
%Y Moniz, Helena
%S Proceedings of the 24th Annual Conference of the European Association for Machine Translation
%D 2023
%8 June
%I European Association for Machine Translation
%C Tampere, Finland
%F sharami-etal-2023-tailoring
%X While quality estimation (QE) can play an important role in the translation process, its effectiveness relies on the availability and quality of training data. For QE in particular, high-quality labeled data is often lacking due to the high-cost and effort associated with labeling such data. Aside from the data scarcity challenge, QE models should also be generalizabile, i.e., they should be able to handle data from different domains, both generic and specific. To alleviate these two main issues — data scarcity and domain mismatch — this paper combines domain adaptation and data augmentation within a robust QE system. Our method is to first train a generic QE model and then fine-tune it on a specific domain while retaining generic knowledge. Our results show a significant improvement for all the language pairs investigated, better cross-lingual inference, and a superior performance in zero-shot learning scenarios as compared to state-of-the-art baselines.
%U https://aclanthology.org/2023.eamt-1.2
%P 9-20
Markdown (Informal)
[Tailoring Domain Adaptation for Machine Translation Quality Estimation](https://aclanthology.org/2023.eamt-1.2) (Sharami et al., EAMT 2023)
ACL
- Javad Pourmostafa Roshan Sharami, Dimitar Shterionov, Frédéric Blain, Eva Vanmassenhove, Mirella De Sisto, Chris Emmery, and Pieter Spronck. 2023. Tailoring Domain Adaptation for Machine Translation Quality Estimation. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation, pages 9–20, Tampere, Finland. European Association for Machine Translation.