@inproceedings{lu-etal-2018-alibaba,
title = "{A}libaba Submission to the {WMT}18 Parallel Corpus Filtering Task",
author = "Lu, Jun and
Lv, Xiaoyu and
Shi, Yangbin and
Chen, Boxing",
booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
month = oct,
year = "2018",
address = "Belgium, Brussels",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6482",
doi = "10.18653/v1/W18-6481",
pages = "917--922",
abstract = "This paper describes the Alibaba Machine Translation Group submissions to the WMT 2018 Shared Task on Parallel Corpus Filtering. While evaluating the quality of the parallel corpus, the three characteristics of the corpus are investigated, i.e. 1) the bilingual/translation quality, 2) the monolingual quality and 3) the corpus diversity. Both rule-based and model-based methods are adapted to score the parallel sentence pairs. The final parallel corpus filtering system is reliable, easy to build and adapt to other language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2018-alibaba">
<titleInfo>
<title>Alibaba Submission to the WMT18 Parallel Corpus Filtering Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangbin</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boxing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Belgium, Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the Alibaba Machine Translation Group submissions to the WMT 2018 Shared Task on Parallel Corpus Filtering. While evaluating the quality of the parallel corpus, the three characteristics of the corpus are investigated, i.e. 1) the bilingual/translation quality, 2) the monolingual quality and 3) the corpus diversity. Both rule-based and model-based methods are adapted to score the parallel sentence pairs. The final parallel corpus filtering system is reliable, easy to build and adapt to other language pairs.</abstract>
<identifier type="citekey">lu-etal-2018-alibaba</identifier>
<identifier type="doi">10.18653/v1/W18-6481</identifier>
<location>
<url>https://aclanthology.org/W18-6482</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>917</start>
<end>922</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alibaba Submission to the WMT18 Parallel Corpus Filtering Task
%A Lu, Jun
%A Lv, Xiaoyu
%A Shi, Yangbin
%A Chen, Boxing
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 October
%I Association for Computational Linguistics
%C Belgium, Brussels
%F lu-etal-2018-alibaba
%X This paper describes the Alibaba Machine Translation Group submissions to the WMT 2018 Shared Task on Parallel Corpus Filtering. While evaluating the quality of the parallel corpus, the three characteristics of the corpus are investigated, i.e. 1) the bilingual/translation quality, 2) the monolingual quality and 3) the corpus diversity. Both rule-based and model-based methods are adapted to score the parallel sentence pairs. The final parallel corpus filtering system is reliable, easy to build and adapt to other language pairs.
%R 10.18653/v1/W18-6481
%U https://aclanthology.org/W18-6482
%U https://doi.org/10.18653/v1/W18-6481
%P 917-922
Markdown (Informal)
[Alibaba Submission to the WMT18 Parallel Corpus Filtering Task](https://aclanthology.org/W18-6482) (Lu et al., WMT 2018)
ACL