@inproceedings{mi-etal-2017-log,
title = "Log-linear Models for {U}yghur Segmentation in Spoken Language Translation",
author = "Mi, Chenggang and
Yang, Yating and
Dong, Rui and
Zhou, Xi and
Wang, Lei and
Li, Xiao and
Jiang, Tonghai",
booktitle = "Proceedings of the International Conference Recent Advances in Natural Language Processing, {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://doi.org/10.26615/978-954-452-049-6_065",
doi = "10.26615/978-954-452-049-6_065",
pages = "492--500",
abstract = "To alleviate data sparsity in spoken Uyghur machine translation, we proposed a log-linear based morphological segmentation approach. Instead of learning model only from monolingual annotated corpus, this approach optimizes Uyghur segmentation for spoken translation based on both bilingual and monolingual corpus. Our approach relies on several features such as traditional conditional random field (CRF) feature, bilingual word alignment feature and monolingual suffixword co-occurrence feature. Experimental results shown that our proposed segmentation model for Uyghur spoken translation achieved 1.6 BLEU score improvements compared with the state-of-the-art baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mi-etal-2017-log">
<titleInfo>
<title>Log-linear Models for Uyghur Segmentation in Spoken Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenggang</namePart>
<namePart type="family">Mi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yating</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tonghai</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-sep</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
</titleInfo>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To alleviate data sparsity in spoken Uyghur machine translation, we proposed a log-linear based morphological segmentation approach. Instead of learning model only from monolingual annotated corpus, this approach optimizes Uyghur segmentation for spoken translation based on both bilingual and monolingual corpus. Our approach relies on several features such as traditional conditional random field (CRF) feature, bilingual word alignment feature and monolingual suffixword co-occurrence feature. Experimental results shown that our proposed segmentation model for Uyghur spoken translation achieved 1.6 BLEU score improvements compared with the state-of-the-art baseline.</abstract>
<identifier type="citekey">mi-etal-2017-log</identifier>
<identifier type="doi">10.26615/978-954-452-049-6_065</identifier>
<part>
<date>2017-sep</date>
<extent unit="page">
<start>492</start>
<end>500</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Log-linear Models for Uyghur Segmentation in Spoken Language Translation
%A Mi, Chenggang
%A Yang, Yating
%A Dong, Rui
%A Zhou, Xi
%A Wang, Lei
%A Li, Xiao
%A Jiang, Tonghai
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 sep
%I INCOMA Ltd.
%C Varna, Bulgaria
%F mi-etal-2017-log
%X To alleviate data sparsity in spoken Uyghur machine translation, we proposed a log-linear based morphological segmentation approach. Instead of learning model only from monolingual annotated corpus, this approach optimizes Uyghur segmentation for spoken translation based on both bilingual and monolingual corpus. Our approach relies on several features such as traditional conditional random field (CRF) feature, bilingual word alignment feature and monolingual suffixword co-occurrence feature. Experimental results shown that our proposed segmentation model for Uyghur spoken translation achieved 1.6 BLEU score improvements compared with the state-of-the-art baseline.
%R 10.26615/978-954-452-049-6_065
%U https://doi.org/10.26615/978-954-452-049-6_065
%P 492-500
Markdown (Informal)
[Log-linear Models for Uyghur Segmentation in Spoken Language Translation](https://doi.org/10.26615/978-954-452-049-6_065) (Mi et al., RANLP 2017)
ACL
- Chenggang Mi, Yating Yang, Rui Dong, Xi Zhou, Lei Wang, Xiao Li, and Tonghai Jiang. 2017. Log-linear Models for Uyghur Segmentation in Spoken Language Translation. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 492–500, Varna, Bulgaria. INCOMA Ltd..