@inproceedings{gupta-etal-2011-extending,
title = "Extending a probabilistic phrase alignment approach for {SMT}",
author = "Gupta, Mridul and
Hewavitharana, Sanjika and
Vogel, Stephan",
editor = {Federico, Marcello and
Hwang, Mei-Yuh and
R{\"o}dder, Margit and
St{\"u}ker, Sebastian},
booktitle = "Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign",
month = dec # " 8-9",
year = "2011",
address = "San Francisco, California",
url = "https://aclanthology.org/2011.iwslt-evaluation.23",
pages = "175--182",
abstract = "Phrase alignment is a crucial step in phrase-based statistical machine translation. We explore a way of improving phrase alignment by adding syntactic information in the form of chunks as soft constraints guided by an in-depth and detailed analysis on a hand-aligned data set. We extend a probabilistic phrase alignment model that extracts phrase pairs by optimizing phrase pair boundaries over the sentence pair [1]. The boundaries of the target phrase are chosen such that the overall sentence alignment probability is optimal. Viterbi alignment information is also added in the extended model with a view of improving phrase alignment. We extract phrase pairs using a relatively larger number of features which are discriminatively trained using a large-margin online learning algorithm, i.e., Margin Infused Relaxed Algorithm (MIRA) and integrate it in our approach. Initial experiments show improvements in both phrase alignment and translation quality for Arabic-English on a moderate-size translation task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2011-extending">
<titleInfo>
<title>Extending a probabilistic phrase alignment approach for SMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mridul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjika</namePart>
<namePart type="family">Hewavitharana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Vogel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2011-dec 8-9</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei-Yuh</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margit</namePart>
<namePart type="family">Rödder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<place>
<placeTerm type="text">San Francisco, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Phrase alignment is a crucial step in phrase-based statistical machine translation. We explore a way of improving phrase alignment by adding syntactic information in the form of chunks as soft constraints guided by an in-depth and detailed analysis on a hand-aligned data set. We extend a probabilistic phrase alignment model that extracts phrase pairs by optimizing phrase pair boundaries over the sentence pair [1]. The boundaries of the target phrase are chosen such that the overall sentence alignment probability is optimal. Viterbi alignment information is also added in the extended model with a view of improving phrase alignment. We extract phrase pairs using a relatively larger number of features which are discriminatively trained using a large-margin online learning algorithm, i.e., Margin Infused Relaxed Algorithm (MIRA) and integrate it in our approach. Initial experiments show improvements in both phrase alignment and translation quality for Arabic-English on a moderate-size translation task.</abstract>
<identifier type="citekey">gupta-etal-2011-extending</identifier>
<location>
<url>https://aclanthology.org/2011.iwslt-evaluation.23</url>
</location>
<part>
<date>2011-dec 8-9</date>
<extent unit="page">
<start>175</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extending a probabilistic phrase alignment approach for SMT
%A Gupta, Mridul
%A Hewavitharana, Sanjika
%A Vogel, Stephan
%Y Federico, Marcello
%Y Hwang, Mei-Yuh
%Y Rödder, Margit
%Y Stüker, Sebastian
%S Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign
%D 2011
%8 dec 8 9
%C San Francisco, California
%F gupta-etal-2011-extending
%X Phrase alignment is a crucial step in phrase-based statistical machine translation. We explore a way of improving phrase alignment by adding syntactic information in the form of chunks as soft constraints guided by an in-depth and detailed analysis on a hand-aligned data set. We extend a probabilistic phrase alignment model that extracts phrase pairs by optimizing phrase pair boundaries over the sentence pair [1]. The boundaries of the target phrase are chosen such that the overall sentence alignment probability is optimal. Viterbi alignment information is also added in the extended model with a view of improving phrase alignment. We extract phrase pairs using a relatively larger number of features which are discriminatively trained using a large-margin online learning algorithm, i.e., Margin Infused Relaxed Algorithm (MIRA) and integrate it in our approach. Initial experiments show improvements in both phrase alignment and translation quality for Arabic-English on a moderate-size translation task.
%U https://aclanthology.org/2011.iwslt-evaluation.23
%P 175-182
Markdown (Informal)
[Extending a probabilistic phrase alignment approach for SMT](https://aclanthology.org/2011.iwslt-evaluation.23) (Gupta et al., IWSLT 2011)
ACL