@inproceedings{santamaria-axelrod-2017-data,
title = "Data Selection with Cluster-Based Language Difference Models and Cynical Selection",
author = "Santamar{\'\i}a, Luc{\'\i}a and
Axelrod, Amittai",
editor = "Sakti, Sakriani and
Utiyama, Masao",
booktitle = "Proceedings of the 14th International Conference on Spoken Language Translation",
month = dec # " 14-15",
year = "2017",
address = "Tokyo, Japan",
publisher = "International Workshop on Spoken Language Translation",
url = "https://aclanthology.org/2017.iwslt-1.19",
pages = "137--145",
abstract = "We present and apply two methods for addressing the problem of selecting relevant training data out of a general pool for use in tasks such as machine translation. Building on existing work on class-based language difference models [1], we first introduce a cluster-based method that uses Brown clusters to condense the vocabulary of the corpora. Secondly, we implement the cynical data selection method [2], which incrementally constructs a training corpus to efficiently model the task corpus. Both the cluster-based and the cynical data selection approaches are used for the first time within a machine translation system, and we perform a head-to-head comparison. Our intrinsic evaluations show that both new methods outperform the standard Moore-Lewis approach (cross-entropy difference), in terms of better perplexity and OOV rates on in-domain data. The cynical approach converges much quicker, covering nearly all of the in-domain vocabulary with 84{\%} less data than the other methods. Furthermore, the new approaches can be used to select machine translation training data for training better systems. Our results confirm that class-based selection using Brown clusters is a viable alternative to POS-based class-based methods, and removes the reliance on a part-of-speech tagger. Additionally, we are able to validate the recently proposed cynical data selection method, showing that its performance in SMT models surpasses that of traditional cross-entropy difference methods and more closely matches the sentence length of the task corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="santamaria-axelrod-2017-data">
<titleInfo>
<title>Data Selection with Cluster-Based Language Difference Models and Cynical Selection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucía</namePart>
<namePart type="family">Santamaría</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amittai</namePart>
<namePart type="family">Axelrod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-dec 14-15</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Spoken Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Workshop on Spoken Language Translation</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present and apply two methods for addressing the problem of selecting relevant training data out of a general pool for use in tasks such as machine translation. Building on existing work on class-based language difference models [1], we first introduce a cluster-based method that uses Brown clusters to condense the vocabulary of the corpora. Secondly, we implement the cynical data selection method [2], which incrementally constructs a training corpus to efficiently model the task corpus. Both the cluster-based and the cynical data selection approaches are used for the first time within a machine translation system, and we perform a head-to-head comparison. Our intrinsic evaluations show that both new methods outperform the standard Moore-Lewis approach (cross-entropy difference), in terms of better perplexity and OOV rates on in-domain data. The cynical approach converges much quicker, covering nearly all of the in-domain vocabulary with 84% less data than the other methods. Furthermore, the new approaches can be used to select machine translation training data for training better systems. Our results confirm that class-based selection using Brown clusters is a viable alternative to POS-based class-based methods, and removes the reliance on a part-of-speech tagger. Additionally, we are able to validate the recently proposed cynical data selection method, showing that its performance in SMT models surpasses that of traditional cross-entropy difference methods and more closely matches the sentence length of the task corpus.</abstract>
<identifier type="citekey">santamaria-axelrod-2017-data</identifier>
<location>
<url>https://aclanthology.org/2017.iwslt-1.19</url>
</location>
<part>
<date>2017-dec 14-15</date>
<extent unit="page">
<start>137</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Selection with Cluster-Based Language Difference Models and Cynical Selection
%A Santamaría, Lucía
%A Axelrod, Amittai
%Y Sakti, Sakriani
%Y Utiyama, Masao
%S Proceedings of the 14th International Conference on Spoken Language Translation
%D 2017
%8 dec 14 15
%I International Workshop on Spoken Language Translation
%C Tokyo, Japan
%F santamaria-axelrod-2017-data
%X We present and apply two methods for addressing the problem of selecting relevant training data out of a general pool for use in tasks such as machine translation. Building on existing work on class-based language difference models [1], we first introduce a cluster-based method that uses Brown clusters to condense the vocabulary of the corpora. Secondly, we implement the cynical data selection method [2], which incrementally constructs a training corpus to efficiently model the task corpus. Both the cluster-based and the cynical data selection approaches are used for the first time within a machine translation system, and we perform a head-to-head comparison. Our intrinsic evaluations show that both new methods outperform the standard Moore-Lewis approach (cross-entropy difference), in terms of better perplexity and OOV rates on in-domain data. The cynical approach converges much quicker, covering nearly all of the in-domain vocabulary with 84% less data than the other methods. Furthermore, the new approaches can be used to select machine translation training data for training better systems. Our results confirm that class-based selection using Brown clusters is a viable alternative to POS-based class-based methods, and removes the reliance on a part-of-speech tagger. Additionally, we are able to validate the recently proposed cynical data selection method, showing that its performance in SMT models surpasses that of traditional cross-entropy difference methods and more closely matches the sentence length of the task corpus.
%U https://aclanthology.org/2017.iwslt-1.19
%P 137-145
Markdown (Informal)
[Data Selection with Cluster-Based Language Difference Models and Cynical Selection](https://aclanthology.org/2017.iwslt-1.19) (Santamaría & Axelrod, IWSLT 2017)
ACL