@inproceedings{zhang-etal-2014-dual,
title = "Dual Subtitles as Parallel Corpora",
author = "Zhang, Shikun and
Ling, Wang and
Dyer, Chris",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/1199_Paper.pdf",
pages = "1869--1874",
abstract = "In this paper, we leverage the existence of dual subtitles as a source of parallel data. Dual subtitles present viewers with two languages simultaneously, and are generally aligned in the segment level, which removes the need to automatically perform this alignment. This is desirable as extracted parallel data does not contain alignment errors present in previous work that aligns different subtitle files for the same movie. We present a simple heuristic to detect and extract dual subtitles and show that more than 20 million sentence pairs can be extracted for the Mandarin-English language pair. We also show that extracting data from this source can be a viable solution for improving Machine Translation systems in the domain of subtitles.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2014-dual">
<titleInfo>
<title>Dual Subtitles as Parallel Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shikun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we leverage the existence of dual subtitles as a source of parallel data. Dual subtitles present viewers with two languages simultaneously, and are generally aligned in the segment level, which removes the need to automatically perform this alignment. This is desirable as extracted parallel data does not contain alignment errors present in previous work that aligns different subtitle files for the same movie. We present a simple heuristic to detect and extract dual subtitles and show that more than 20 million sentence pairs can be extracted for the Mandarin-English language pair. We also show that extracting data from this source can be a viable solution for improving Machine Translation systems in the domain of subtitles.</abstract>
<identifier type="citekey">zhang-etal-2014-dual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1199_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1869</start>
<end>1874</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dual Subtitles as Parallel Corpora
%A Zhang, Shikun
%A Ling, Wang
%A Dyer, Chris
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F zhang-etal-2014-dual
%X In this paper, we leverage the existence of dual subtitles as a source of parallel data. Dual subtitles present viewers with two languages simultaneously, and are generally aligned in the segment level, which removes the need to automatically perform this alignment. This is desirable as extracted parallel data does not contain alignment errors present in previous work that aligns different subtitle files for the same movie. We present a simple heuristic to detect and extract dual subtitles and show that more than 20 million sentence pairs can be extracted for the Mandarin-English language pair. We also show that extracting data from this source can be a viable solution for improving Machine Translation systems in the domain of subtitles.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1199_Paper.pdf
%P 1869-1874
Markdown (Informal)
[Dual Subtitles as Parallel Corpora](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1199_Paper.pdf) (Zhang et al., LREC 2014)
ACL
- Shikun Zhang, Wang Ling, and Chris Dyer. 2014. Dual Subtitles as Parallel Corpora. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1869–1874, Reykjavik, Iceland. European Language Resources Association (ELRA).