@inproceedings{zhang-etal-2014-probabilistic,
title = "A probabilistic feature-based fill-up for {SMT}",
author = "Zhang, Jian and
Li, Liangyou and
Way, Andy and
Liu, Qun",
editor = "Al-Onaizan, Yaser and
Simard, Michel",
booktitle = "Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track",
month = oct # " 22-26",
year = "2014",
address = "Vancouver, Canada",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2014.amta-researchers.8",
pages = "96--109",
abstract = "In this paper, we describe an effective translation model combination approach based on the estimation of a probabilistic Support Vector Machine (SVM). We collect domain knowledge from both in-domain and general-domain corpora inspired by a commonly used data selection algorithm, which we then use as features for the SVM training. Drawing on previous work on binary-featured phrase table fill-up (Nakov, 2008; Bisazza et al., 2011), we substitute the binary feature in the original work with our probabilistic domain-likeness feature. Later, we design two experiments to evaluate the proposed probabilistic feature-based approach on the French-to-English language pair using data provided at WMT07, WMT13 and IWLST11 translation tasks. Our experiments demonstrate that translation performance can gain significant improvements of up to +0.36 and +0.82 BLEU scores by using our probabilistic feature-based translation model fill-up approach compared with the binary featured fill-up approach in both experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2014-probabilistic">
<titleInfo>
<title>A probabilistic feature-based fill-up for SMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangyou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Way</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-oct 22-26</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Simard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe an effective translation model combination approach based on the estimation of a probabilistic Support Vector Machine (SVM). We collect domain knowledge from both in-domain and general-domain corpora inspired by a commonly used data selection algorithm, which we then use as features for the SVM training. Drawing on previous work on binary-featured phrase table fill-up (Nakov, 2008; Bisazza et al., 2011), we substitute the binary feature in the original work with our probabilistic domain-likeness feature. Later, we design two experiments to evaluate the proposed probabilistic feature-based approach on the French-to-English language pair using data provided at WMT07, WMT13 and IWLST11 translation tasks. Our experiments demonstrate that translation performance can gain significant improvements of up to +0.36 and +0.82 BLEU scores by using our probabilistic feature-based translation model fill-up approach compared with the binary featured fill-up approach in both experiments.</abstract>
<identifier type="citekey">zhang-etal-2014-probabilistic</identifier>
<location>
<url>https://aclanthology.org/2014.amta-researchers.8</url>
</location>
<part>
<date>2014-oct 22-26</date>
<extent unit="page">
<start>96</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A probabilistic feature-based fill-up for SMT
%A Zhang, Jian
%A Li, Liangyou
%A Way, Andy
%A Liu, Qun
%Y Al-Onaizan, Yaser
%Y Simard, Michel
%S Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track
%D 2014
%8 oct 22 26
%I Association for Machine Translation in the Americas
%C Vancouver, Canada
%F zhang-etal-2014-probabilistic
%X In this paper, we describe an effective translation model combination approach based on the estimation of a probabilistic Support Vector Machine (SVM). We collect domain knowledge from both in-domain and general-domain corpora inspired by a commonly used data selection algorithm, which we then use as features for the SVM training. Drawing on previous work on binary-featured phrase table fill-up (Nakov, 2008; Bisazza et al., 2011), we substitute the binary feature in the original work with our probabilistic domain-likeness feature. Later, we design two experiments to evaluate the proposed probabilistic feature-based approach on the French-to-English language pair using data provided at WMT07, WMT13 and IWLST11 translation tasks. Our experiments demonstrate that translation performance can gain significant improvements of up to +0.36 and +0.82 BLEU scores by using our probabilistic feature-based translation model fill-up approach compared with the binary featured fill-up approach in both experiments.
%U https://aclanthology.org/2014.amta-researchers.8
%P 96-109
Markdown (Informal)
[A probabilistic feature-based fill-up for SMT](https://aclanthology.org/2014.amta-researchers.8) (Zhang et al., AMTA 2014)
ACL
- Jian Zhang, Liangyou Li, Andy Way, and Qun Liu. 2014. A probabilistic feature-based fill-up for SMT. In Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track, pages 96–109, Vancouver, Canada. Association for Machine Translation in the Americas.