@inproceedings{sen-etal-2019-parallel,
title = "Parallel Corpus Filtering Based on Fuzzy String Matching",
author = "Sen, Sukanta and
Ekbal, Asif and
Bhattacharyya, Pushpak",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5440",
doi = "10.18653/v1/W19-5440",
pages = "289--293",
abstract = "In this paper, we describe the IIT Patna{'}s submission to WMT 2019 shared task on parallel corpus filtering. This shared task asks the participants to develop methods for scoring each parallel sentence from a given noisy parallel corpus. Quality of the scoring method is judged based on the quality of SMT and NMT systems trained on smaller set of high-quality parallel sentences sub-sampled from the original noisy corpus. This task has two language pairs. We submit for both the Nepali-English and Sinhala-English language pairs. We define fuzzy string matching score between English and the translated (into English) source based on Levenshtein distance. Based on the scores, we sub-sample two sets (having 1 million and 5 millions English tokens) of parallel sentences from each parallel corpus, and train SMT systems for development purpose only. The organizers publish the official evaluation using both SMT and NMT on the final official test set. Total 10 teams participated in the shared task and according the official evaluation, our scoring method obtains 2nd position in the team ranking for 1-million NepaliEnglish NMT and 5-million Sinhala-English NMT categories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sen-etal-2019-parallel">
<titleInfo>
<title>Parallel Corpus Filtering Based on Fuzzy String Matching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sukanta</namePart>
<namePart type="family">Sen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe the IIT Patna’s submission to WMT 2019 shared task on parallel corpus filtering. This shared task asks the participants to develop methods for scoring each parallel sentence from a given noisy parallel corpus. Quality of the scoring method is judged based on the quality of SMT and NMT systems trained on smaller set of high-quality parallel sentences sub-sampled from the original noisy corpus. This task has two language pairs. We submit for both the Nepali-English and Sinhala-English language pairs. We define fuzzy string matching score between English and the translated (into English) source based on Levenshtein distance. Based on the scores, we sub-sample two sets (having 1 million and 5 millions English tokens) of parallel sentences from each parallel corpus, and train SMT systems for development purpose only. The organizers publish the official evaluation using both SMT and NMT on the final official test set. Total 10 teams participated in the shared task and according the official evaluation, our scoring method obtains 2nd position in the team ranking for 1-million NepaliEnglish NMT and 5-million Sinhala-English NMT categories.</abstract>
<identifier type="citekey">sen-etal-2019-parallel</identifier>
<identifier type="doi">10.18653/v1/W19-5440</identifier>
<location>
<url>https://aclanthology.org/W19-5440</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>289</start>
<end>293</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel Corpus Filtering Based on Fuzzy String Matching
%A Sen, Sukanta
%A Ekbal, Asif
%A Bhattacharyya, Pushpak
%Y Bojar, Ondřej
%Y Chatterjee, Rajen
%Y Federmann, Christian
%Y Fishel, Mark
%Y Graham, Yvette
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F sen-etal-2019-parallel
%X In this paper, we describe the IIT Patna’s submission to WMT 2019 shared task on parallel corpus filtering. This shared task asks the participants to develop methods for scoring each parallel sentence from a given noisy parallel corpus. Quality of the scoring method is judged based on the quality of SMT and NMT systems trained on smaller set of high-quality parallel sentences sub-sampled from the original noisy corpus. This task has two language pairs. We submit for both the Nepali-English and Sinhala-English language pairs. We define fuzzy string matching score between English and the translated (into English) source based on Levenshtein distance. Based on the scores, we sub-sample two sets (having 1 million and 5 millions English tokens) of parallel sentences from each parallel corpus, and train SMT systems for development purpose only. The organizers publish the official evaluation using both SMT and NMT on the final official test set. Total 10 teams participated in the shared task and according the official evaluation, our scoring method obtains 2nd position in the team ranking for 1-million NepaliEnglish NMT and 5-million Sinhala-English NMT categories.
%R 10.18653/v1/W19-5440
%U https://aclanthology.org/W19-5440
%U https://doi.org/10.18653/v1/W19-5440
%P 289-293
Markdown (Informal)
[Parallel Corpus Filtering Based on Fuzzy String Matching](https://aclanthology.org/W19-5440) (Sen et al., WMT 2019)
ACL
- Sukanta Sen, Asif Ekbal, and Pushpak Bhattacharyya. 2019. Parallel Corpus Filtering Based on Fuzzy String Matching. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pages 289–293, Florence, Italy. Association for Computational Linguistics.