@inproceedings{park-etal-2022-dalc,
title = "{D}a{LC}: Domain Adaptation Learning Curve Prediction for Neural Machine Translation",
author = "Park, Cheonbok and
Kim, Hantae and
Calapodescu, Ioan and
Cho, Hyun Chang and
Nikoulina, Vassilina",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.141/",
doi = "10.18653/v1/2022.findings-acl.141",
pages = "1789--1807",
abstract = "Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data. Without parallel data, there is no way to estimate the potential benefit of DA, nor the amount of parallel samples it would require. It is however a desirable functionality that could help MT practitioners to make an informed decision before investing resources in dataset creation. We propose a Domain adaptation Learning Curve prediction (DaLC) model that predicts prospective DA performance based on in-domain monolingual samples in the source language. Our model relies on the NMT encoder representations combined with various instance and corpus-level features. We demonstrate that instance-level is better able to distinguish between different domains compared to corpus-level frameworks proposed in previous studies Finally, we perform in-depth analyses of the results highlighting the limitations of our approach, and provide directions for future research."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2022-dalc">
<titleInfo>
<title>DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheonbok</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hantae</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioan</namePart>
<namePart type="family">Calapodescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyun</namePart>
<namePart type="given">Chang</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vassilina</namePart>
<namePart type="family">Nikoulina</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>Findings of the Association for Computational Linguistics: ACL 2022</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>Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data. Without parallel data, there is no way to estimate the potential benefit of DA, nor the amount of parallel samples it would require. It is however a desirable functionality that could help MT practitioners to make an informed decision before investing resources in dataset creation. We propose a Domain adaptation Learning Curve prediction (DaLC) model that predicts prospective DA performance based on in-domain monolingual samples in the source language. Our model relies on the NMT encoder representations combined with various instance and corpus-level features. We demonstrate that instance-level is better able to distinguish between different domains compared to corpus-level frameworks proposed in previous studies Finally, we perform in-depth analyses of the results highlighting the limitations of our approach, and provide directions for future research.</abstract>
<identifier type="citekey">park-etal-2022-dalc</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.141</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.141/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1789</start>
<end>1807</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation
%A Park, Cheonbok
%A Kim, Hantae
%A Calapodescu, Ioan
%A Cho, Hyun Chang
%A Nikoulina, Vassilina
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F park-etal-2022-dalc
%X Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data. Without parallel data, there is no way to estimate the potential benefit of DA, nor the amount of parallel samples it would require. It is however a desirable functionality that could help MT practitioners to make an informed decision before investing resources in dataset creation. We propose a Domain adaptation Learning Curve prediction (DaLC) model that predicts prospective DA performance based on in-domain monolingual samples in the source language. Our model relies on the NMT encoder representations combined with various instance and corpus-level features. We demonstrate that instance-level is better able to distinguish between different domains compared to corpus-level frameworks proposed in previous studies Finally, we perform in-depth analyses of the results highlighting the limitations of our approach, and provide directions for future research.
%R 10.18653/v1/2022.findings-acl.141
%U https://aclanthology.org/2022.findings-acl.141/
%U https://doi.org/10.18653/v1/2022.findings-acl.141
%P 1789-1807
Markdown (Informal)
[DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation](https://aclanthology.org/2022.findings-acl.141/) (Park et al., Findings 2022)
ACL