@inproceedings{stojanovski-fraser-2021-addressing,
title = "Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation",
author = "Stojanovski, Dario and
Fraser, Alexander",
editor = "Ben-David, Eyal and
Cohen, Shay and
McDonald, Ryan and
Plank, Barbara and
Reichart, Roi and
Rotman, Guy and
Ziser, Yftah",
booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",
month = apr,
year = "2021",
address = "Kyiv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.adaptnlp-1.9",
pages = "80--93",
abstract = "Achieving satisfying performance in machine translation on domains for which there is no training data is challenging. Traditional supervised domain adaptation is not suitable for addressing such zero-resource domains because it relies on in-domain parallel data. We show that when in-domain parallel data is not available, access to document-level context enables better capturing of domain generalities compared to only having access to a single sentence. Having access to more information provides a more reliable domain estimation. We present two document-level Transformer models which are capable of using large context sizes and we compare these models against strong Transformer baselines. We obtain improvements for the two zero-resource domains we study. We additionally provide an analysis where we vary the amount of context and look at the case where in-domain data is available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stojanovski-fraser-2021-addressing">
<titleInfo>
<title>Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dario</namePart>
<namePart type="family">Stojanovski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Domain Adaptation for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eyal</namePart>
<namePart type="family">Ben-David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">McDonald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Rotman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yftah</namePart>
<namePart type="family">Ziser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Achieving satisfying performance in machine translation on domains for which there is no training data is challenging. Traditional supervised domain adaptation is not suitable for addressing such zero-resource domains because it relies on in-domain parallel data. We show that when in-domain parallel data is not available, access to document-level context enables better capturing of domain generalities compared to only having access to a single sentence. Having access to more information provides a more reliable domain estimation. We present two document-level Transformer models which are capable of using large context sizes and we compare these models against strong Transformer baselines. We obtain improvements for the two zero-resource domains we study. We additionally provide an analysis where we vary the amount of context and look at the case where in-domain data is available.</abstract>
<identifier type="citekey">stojanovski-fraser-2021-addressing</identifier>
<location>
<url>https://aclanthology.org/2021.adaptnlp-1.9</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>80</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation
%A Stojanovski, Dario
%A Fraser, Alexander
%Y Ben-David, Eyal
%Y Cohen, Shay
%Y McDonald, Ryan
%Y Plank, Barbara
%Y Reichart, Roi
%Y Rotman, Guy
%Y Ziser, Yftah
%S Proceedings of the Second Workshop on Domain Adaptation for NLP
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv, Ukraine
%F stojanovski-fraser-2021-addressing
%X Achieving satisfying performance in machine translation on domains for which there is no training data is challenging. Traditional supervised domain adaptation is not suitable for addressing such zero-resource domains because it relies on in-domain parallel data. We show that when in-domain parallel data is not available, access to document-level context enables better capturing of domain generalities compared to only having access to a single sentence. Having access to more information provides a more reliable domain estimation. We present two document-level Transformer models which are capable of using large context sizes and we compare these models against strong Transformer baselines. We obtain improvements for the two zero-resource domains we study. We additionally provide an analysis where we vary the amount of context and look at the case where in-domain data is available.
%U https://aclanthology.org/2021.adaptnlp-1.9
%P 80-93
Markdown (Informal)
[Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation](https://aclanthology.org/2021.adaptnlp-1.9) (Stojanovski & Fraser, AdaptNLP 2021)
ACL