@inproceedings{ruiz-federico-2012-mdi,
title = "{MDI} adaptation for the lazy: avoiding normalization in {LM} adaptation for lecture translation",
author = "Ruiz, Nick and
Federico, Marcello",
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.14/",
pages = "244--251",
abstract = "This paper provides a fast alternative to Minimum Discrimination Information-based language model adaptation for statistical machine translation. We provide an alternative to computing a normalization term that requires computing full model probabilities (including back-off probabilities) for all n-grams. Rather than re-estimating an entire language model, our Lazy MDI approach leverages a smoothed unigram ratio between an adaptation text and the background language model to scale only the n-gram probabilities corresponding to translation options gathered by the SMT decoder. The effects of the unigram ratio are scaled by adding an additional feature weight to the log-linear discriminative model. We present results on the IWSLT 2012 TED talk translation task and show that Lazy MDI provides comparable language model adaptation performance to classic MDI."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruiz-federico-2012-mdi">
<titleInfo>
<title>MDI adaptation for the lazy: avoiding normalization in LM adaptation for lecture translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nick</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</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>This paper provides a fast alternative to Minimum Discrimination Information-based language model adaptation for statistical machine translation. We provide an alternative to computing a normalization term that requires computing full model probabilities (including back-off probabilities) for all n-grams. Rather than re-estimating an entire language model, our Lazy MDI approach leverages a smoothed unigram ratio between an adaptation text and the background language model to scale only the n-gram probabilities corresponding to translation options gathered by the SMT decoder. The effects of the unigram ratio are scaled by adding an additional feature weight to the log-linear discriminative model. We present results on the IWSLT 2012 TED talk translation task and show that Lazy MDI provides comparable language model adaptation performance to classic MDI.</abstract>
<identifier type="citekey">ruiz-federico-2012-mdi</identifier>
<location>
<url>https://aclanthology.org/2012.iwslt-papers.14/</url>
</location>
<part>
<date>2012-dec 6-7</date>
<extent unit="page">
<start>244</start>
<end>251</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MDI adaptation for the lazy: avoiding normalization in LM adaptation for lecture translation
%A Ruiz, Nick
%A Federico, Marcello
%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 ruiz-federico-2012-mdi
%X This paper provides a fast alternative to Minimum Discrimination Information-based language model adaptation for statistical machine translation. We provide an alternative to computing a normalization term that requires computing full model probabilities (including back-off probabilities) for all n-grams. Rather than re-estimating an entire language model, our Lazy MDI approach leverages a smoothed unigram ratio between an adaptation text and the background language model to scale only the n-gram probabilities corresponding to translation options gathered by the SMT decoder. The effects of the unigram ratio are scaled by adding an additional feature weight to the log-linear discriminative model. We present results on the IWSLT 2012 TED talk translation task and show that Lazy MDI provides comparable language model adaptation performance to classic MDI.
%U https://aclanthology.org/2012.iwslt-papers.14/
%P 244-251
Markdown (Informal)
[MDI adaptation for the lazy: avoiding normalization in LM adaptation for lecture translation](https://aclanthology.org/2012.iwslt-papers.14/) (Ruiz & Federico, IWSLT 2012)
ACL