@inproceedings{hardt-elming-2010-incremental,
title = "Incremental Re-training for Post-editing {SMT}",
author = "Hardt, Daniel and
Elming, Jakob",
booktitle = "Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers",
month = oct # " 31-" # nov # " 4",
year = "2010",
address = "Denver, Colorado, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2010.amta-papers.21",
abstract = "A method is presented for incremental re-training of an SMT system, in which a local phrase table is created and incrementally updated as a file is translated and post-edited. It is shown that translation data from within the same file has higher value than other domain-specific data. In two technical domains, within-file data increases BLEU score by several full points. Furthermore, a strong recency effect is documented; nearby data within the file has greater value than more distant data. It is also shown that the value of translation data is strongly correlated with a metric defined over new occurrences of n-grams. Finally, it is argued that the incremental re-training prototype could serve as the basis for a practical system which could be interactively updated in real time in a post-editing setting. Based on the results here, such an interactive system has the potential to dramatically improve translation quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hardt-elming-2010-incremental">
<titleInfo>
<title>Incremental Re-training for Post-editing SMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hardt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Elming</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-oct 31-nov 4</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Denver, Colorado, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A method is presented for incremental re-training of an SMT system, in which a local phrase table is created and incrementally updated as a file is translated and post-edited. It is shown that translation data from within the same file has higher value than other domain-specific data. In two technical domains, within-file data increases BLEU score by several full points. Furthermore, a strong recency effect is documented; nearby data within the file has greater value than more distant data. It is also shown that the value of translation data is strongly correlated with a metric defined over new occurrences of n-grams. Finally, it is argued that the incremental re-training prototype could serve as the basis for a practical system which could be interactively updated in real time in a post-editing setting. Based on the results here, such an interactive system has the potential to dramatically improve translation quality.</abstract>
<identifier type="citekey">hardt-elming-2010-incremental</identifier>
<location>
<url>https://aclanthology.org/2010.amta-papers.21</url>
</location>
<part>
<date>2010-oct 31-nov 4</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incremental Re-training for Post-editing SMT
%A Hardt, Daniel
%A Elming, Jakob
%S Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers
%D 2010
%8 oct 31 nov 4
%I Association for Machine Translation in the Americas
%C Denver, Colorado, USA
%F hardt-elming-2010-incremental
%X A method is presented for incremental re-training of an SMT system, in which a local phrase table is created and incrementally updated as a file is translated and post-edited. It is shown that translation data from within the same file has higher value than other domain-specific data. In two technical domains, within-file data increases BLEU score by several full points. Furthermore, a strong recency effect is documented; nearby data within the file has greater value than more distant data. It is also shown that the value of translation data is strongly correlated with a metric defined over new occurrences of n-grams. Finally, it is argued that the incremental re-training prototype could serve as the basis for a practical system which could be interactively updated in real time in a post-editing setting. Based on the results here, such an interactive system has the potential to dramatically improve translation quality.
%U https://aclanthology.org/2010.amta-papers.21
Markdown (Informal)
[Incremental Re-training for Post-editing SMT](https://aclanthology.org/2010.amta-papers.21) (Hardt & Elming, AMTA 2010)
ACL
- Daniel Hardt and Jakob Elming. 2010. Incremental Re-training for Post-editing SMT. In Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers, Denver, Colorado, USA. Association for Machine Translation in the Americas.