@inproceedings{schulz-aziz-2016-fast,
title = "Fast Collocation-Based {B}ayesian {HMM} Word Alignment",
author = "Schulz, Philip and
Aziz, Wilker",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1296",
pages = "3146--3155",
abstract = "We present a new Bayesian HMM word alignment model for statistical machine translation. The model is a mixture of an alignment model and a language model. The alignment component is a Bayesian extension of the standard HMM. The language model component is responsible for the generation of words needed for source fluency reasons from source language context. This allows for untranslatable source words to remain unaligned and at the same time avoids the introduction of artificial NULL words which introduces unusually long alignment jumps. Existing Bayesian word alignment models are unpractically slow because they consider each target position when resampling a given alignment link. The sampling complexity therefore grows linearly in the target sentence length. In order to make our model useful in practice, we devise an auxiliary variable Gibbs sampler that allows us to resample alignment links in constant time independently of the target sentence length. This leads to considerable speed improvements. Experimental results show that our model performs as well as existing word alignment toolkits in terms of resulting BLEU score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schulz-aziz-2016-fast">
<titleInfo>
<title>Fast Collocation-Based Bayesian HMM Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Schulz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new Bayesian HMM word alignment model for statistical machine translation. The model is a mixture of an alignment model and a language model. The alignment component is a Bayesian extension of the standard HMM. The language model component is responsible for the generation of words needed for source fluency reasons from source language context. This allows for untranslatable source words to remain unaligned and at the same time avoids the introduction of artificial NULL words which introduces unusually long alignment jumps. Existing Bayesian word alignment models are unpractically slow because they consider each target position when resampling a given alignment link. The sampling complexity therefore grows linearly in the target sentence length. In order to make our model useful in practice, we devise an auxiliary variable Gibbs sampler that allows us to resample alignment links in constant time independently of the target sentence length. This leads to considerable speed improvements. Experimental results show that our model performs as well as existing word alignment toolkits in terms of resulting BLEU score.</abstract>
<identifier type="citekey">schulz-aziz-2016-fast</identifier>
<location>
<url>https://aclanthology.org/C16-1296</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>3146</start>
<end>3155</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fast Collocation-Based Bayesian HMM Word Alignment
%A Schulz, Philip
%A Aziz, Wilker
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F schulz-aziz-2016-fast
%X We present a new Bayesian HMM word alignment model for statistical machine translation. The model is a mixture of an alignment model and a language model. The alignment component is a Bayesian extension of the standard HMM. The language model component is responsible for the generation of words needed for source fluency reasons from source language context. This allows for untranslatable source words to remain unaligned and at the same time avoids the introduction of artificial NULL words which introduces unusually long alignment jumps. Existing Bayesian word alignment models are unpractically slow because they consider each target position when resampling a given alignment link. The sampling complexity therefore grows linearly in the target sentence length. In order to make our model useful in practice, we devise an auxiliary variable Gibbs sampler that allows us to resample alignment links in constant time independently of the target sentence length. This leads to considerable speed improvements. Experimental results show that our model performs as well as existing word alignment toolkits in terms of resulting BLEU score.
%U https://aclanthology.org/C16-1296
%P 3146-3155
Markdown (Informal)
[Fast Collocation-Based Bayesian HMM Word Alignment](https://aclanthology.org/C16-1296) (Schulz & Aziz, COLING 2016)
ACL
- Philip Schulz and Wilker Aziz. 2016. Fast Collocation-Based Bayesian HMM Word Alignment. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3146–3155, Osaka, Japan. The COLING 2016 Organizing Committee.