@inproceedings{potet-etal-2012-towards,
title = "Towards a better understanding of statistical post-editing",
author = "Potet, Marion and
Besacier, Laurent and
Blanchon, Herv{\'e} and
Azouzi, Marwen",
booktitle = "Proceedings of the 9th International Workshop on Spoken Language Translation: Papers",
month = dec # " 6-7",
year = "2012",
address = "Hong Kong, Table of contents",
url = "https://aclanthology.org/2012.iwslt-papers.19/",
pages = "284--291",
abstract = "We describe several experiments to better understand the usefulness of statistical post-edition (SPE) to improve phrase-based statistical MT (PBMT) systems raw outputs. Whatever the size of the training corpus, we show that SPE systems trained on general domain data offers no breakthrough to our baseline general domain PBMT system. However, using manually post-edited system outputs to train the SPE led to a slight improvement in the translations quality compared with the use of professional reference translations. We also show that SPE is far more effective for domain adaptation, mainly because it recovers a lot of specific terms unknown to our general PBMT system. Finally, we compare two domain adaptation techniques, post-editing a general domain PBMT system vs building a new domain-adapted PBMT system with two different techniques, and show that the latter outperforms the first one. Yet, when the PBMT is a {\textquotedblleft}black box{\textquotedblright}, SPE trained with post-edited system outputs remains an interesting option for domain adaptation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="potet-etal-2012-towards">
<titleInfo>
<title>Towards a better understanding of statistical post-editing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marion</namePart>
<namePart type="family">Potet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hervé</namePart>
<namePart type="family">Blanchon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marwen</namePart>
<namePart type="family">Azouzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-dec 6-7</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th International Workshop on Spoken Language Translation: Papers</title>
</titleInfo>
<originInfo>
<place>
<placeTerm type="text">Hong Kong, Table of contents</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe several experiments to better understand the usefulness of statistical post-edition (SPE) to improve phrase-based statistical MT (PBMT) systems raw outputs. Whatever the size of the training corpus, we show that SPE systems trained on general domain data offers no breakthrough to our baseline general domain PBMT system. However, using manually post-edited system outputs to train the SPE led to a slight improvement in the translations quality compared with the use of professional reference translations. We also show that SPE is far more effective for domain adaptation, mainly because it recovers a lot of specific terms unknown to our general PBMT system. Finally, we compare two domain adaptation techniques, post-editing a general domain PBMT system vs building a new domain-adapted PBMT system with two different techniques, and show that the latter outperforms the first one. Yet, when the PBMT is a “black box”, SPE trained with post-edited system outputs remains an interesting option for domain adaptation.</abstract>
<identifier type="citekey">potet-etal-2012-towards</identifier>
<location>
<url>https://aclanthology.org/2012.iwslt-papers.19/</url>
</location>
<part>
<date>2012-dec 6-7</date>
<extent unit="page">
<start>284</start>
<end>291</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a better understanding of statistical post-editing
%A Potet, Marion
%A Besacier, Laurent
%A Blanchon, Hervé
%A Azouzi, Marwen
%S Proceedings of the 9th International Workshop on Spoken Language Translation: Papers
%D 2012
%8 dec 6 7
%C Hong Kong, Table of contents
%F potet-etal-2012-towards
%X We describe several experiments to better understand the usefulness of statistical post-edition (SPE) to improve phrase-based statistical MT (PBMT) systems raw outputs. Whatever the size of the training corpus, we show that SPE systems trained on general domain data offers no breakthrough to our baseline general domain PBMT system. However, using manually post-edited system outputs to train the SPE led to a slight improvement in the translations quality compared with the use of professional reference translations. We also show that SPE is far more effective for domain adaptation, mainly because it recovers a lot of specific terms unknown to our general PBMT system. Finally, we compare two domain adaptation techniques, post-editing a general domain PBMT system vs building a new domain-adapted PBMT system with two different techniques, and show that the latter outperforms the first one. Yet, when the PBMT is a “black box”, SPE trained with post-edited system outputs remains an interesting option for domain adaptation.
%U https://aclanthology.org/2012.iwslt-papers.19/
%P 284-291
Markdown (Informal)
[Towards a better understanding of statistical post-editing](https://aclanthology.org/2012.iwslt-papers.19/) (Potet et al., IWSLT 2012)
ACL