@inproceedings{kothur-etal-2018-document,
title = "Document-Level Adaptation for Neural Machine Translation",
author = "Kothur, Sachith Sri Ram and
Knowles, Rebecca and
Koehn, Philipp",
editor = "Birch, Alexandra and
Finch, Andrew and
Luong, Thang and
Neubig, Graham and
Oda, Yusuke",
booktitle = "Proceedings of the 2nd Workshop on Neural Machine Translation and Generation",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-2708",
doi = "10.18653/v1/W18-2708",
pages = "64--73",
abstract = "It is common practice to adapt machine translation systems to novel domains, but even a well-adapted system may be able to perform better on a particular document if it were to learn from a translator{'}s corrections within the document itself. We focus on adaptation within a single document {--} appropriate for an interactive translation scenario where a model adapts to a human translator{'}s input over the course of a document. We propose two methods: single-sentence adaptation (which performs online adaptation one sentence at a time) and dictionary adaptation (which specifically addresses the issue of translating novel words). Combining the two models results in improvements over both approaches individually, and over baseline systems, even on short documents. On WMT news test data, we observe an improvement of +1.8 BLEU points and +23.3{\%} novel word translation accuracy and on EMEA data (descriptions of medications) we observe an improvement of +2.7 BLEU points and +49.2{\%} novel word translation accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kothur-etal-2018-document">
<titleInfo>
<title>Document-Level Adaptation for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sachith</namePart>
<namePart type="given">Sri</namePart>
<namePart type="given">Ram</namePart>
<namePart type="family">Kothur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Knowles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Neural Machine Translation and Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thang</namePart>
<namePart type="family">Luong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Oda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>It is common practice to adapt machine translation systems to novel domains, but even a well-adapted system may be able to perform better on a particular document if it were to learn from a translator’s corrections within the document itself. We focus on adaptation within a single document – appropriate for an interactive translation scenario where a model adapts to a human translator’s input over the course of a document. We propose two methods: single-sentence adaptation (which performs online adaptation one sentence at a time) and dictionary adaptation (which specifically addresses the issue of translating novel words). Combining the two models results in improvements over both approaches individually, and over baseline systems, even on short documents. On WMT news test data, we observe an improvement of +1.8 BLEU points and +23.3% novel word translation accuracy and on EMEA data (descriptions of medications) we observe an improvement of +2.7 BLEU points and +49.2% novel word translation accuracy.</abstract>
<identifier type="citekey">kothur-etal-2018-document</identifier>
<identifier type="doi">10.18653/v1/W18-2708</identifier>
<location>
<url>https://aclanthology.org/W18-2708</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>64</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document-Level Adaptation for Neural Machine Translation
%A Kothur, Sachith Sri Ram
%A Knowles, Rebecca
%A Koehn, Philipp
%Y Birch, Alexandra
%Y Finch, Andrew
%Y Luong, Thang
%Y Neubig, Graham
%Y Oda, Yusuke
%S Proceedings of the 2nd Workshop on Neural Machine Translation and Generation
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F kothur-etal-2018-document
%X It is common practice to adapt machine translation systems to novel domains, but even a well-adapted system may be able to perform better on a particular document if it were to learn from a translator’s corrections within the document itself. We focus on adaptation within a single document – appropriate for an interactive translation scenario where a model adapts to a human translator’s input over the course of a document. We propose two methods: single-sentence adaptation (which performs online adaptation one sentence at a time) and dictionary adaptation (which specifically addresses the issue of translating novel words). Combining the two models results in improvements over both approaches individually, and over baseline systems, even on short documents. On WMT news test data, we observe an improvement of +1.8 BLEU points and +23.3% novel word translation accuracy and on EMEA data (descriptions of medications) we observe an improvement of +2.7 BLEU points and +49.2% novel word translation accuracy.
%R 10.18653/v1/W18-2708
%U https://aclanthology.org/W18-2708
%U https://doi.org/10.18653/v1/W18-2708
%P 64-73
Markdown (Informal)
[Document-Level Adaptation for Neural Machine Translation](https://aclanthology.org/W18-2708) (Kothur et al., NGT 2018)
ACL
- Sachith Sri Ram Kothur, Rebecca Knowles, and Philipp Koehn. 2018. Document-Level Adaptation for Neural Machine Translation. In Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pages 64–73, Melbourne, Australia. Association for Computational Linguistics.