@inproceedings{aulamo-etal-2023-unsupervised,
title = "Unsupervised Feature Selection for Effective Parallel Corpus Filtering",
author = {Aulamo, Mikko and
de Gibert, Ona and
Virpioja, Sami and
Tiedemann, J{\"o}rg},
editor = "Nurminen, Mary and
Brenner, Judith and
Koponen, Maarit and
Latomaa, Sirkku and
Mikhailov, Mikhail and
Schierl, Frederike and
Ranasinghe, Tharindu and
Vanmassenhove, Eva and
Vidal, Sergi Alvarez and
Aranberri, Nora and
Nunziatini, Mara and
Escart{\'i}n, Carla Parra and
Forcada, Mikel and
Popovic, Maja and
Scarton, Carolina and
Moniz, Helena",
booktitle = "Proceedings of the 24th Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2023",
address = "Tampere, Finland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2023.eamt-1.4/",
pages = "31--38",
abstract = "This work presents an unsupervised method of selecting filters and threshold values for the OpusFilter parallel corpus cleaning toolbox. The method clusters sentence pairs into noisy and clean categories and uses the features of the noisy cluster center as filtering parameters. Our approach utilizes feature importance analysis to disregard filters that do not differentiate between clean and noisy data. A randomly sampled subset of a given corpus is used for filter selection and ineffective filters are not run for the full corpus. We use a set of automatic evaluation metrics to assess the quality of translation models trained with data filtered by our method and data filtered with OpusFilter`s default parameters. The trained models cover English-German and English-Ukrainian in both directions. The proposed method outperforms the default parameters in all translation directions for almost all evaluation metrics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aulamo-etal-2023-unsupervised">
<titleInfo>
<title>Unsupervised Feature Selection for Effective Parallel Corpus Filtering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Aulamo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sami</namePart>
<namePart type="family">Virpioja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Brenner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirkku</namePart>
<namePart type="family">Latomaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederike</namePart>
<namePart type="family">Schierl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="given">Alvarez</namePart>
<namePart type="family">Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Nunziatini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tampere, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work presents an unsupervised method of selecting filters and threshold values for the OpusFilter parallel corpus cleaning toolbox. The method clusters sentence pairs into noisy and clean categories and uses the features of the noisy cluster center as filtering parameters. Our approach utilizes feature importance analysis to disregard filters that do not differentiate between clean and noisy data. A randomly sampled subset of a given corpus is used for filter selection and ineffective filters are not run for the full corpus. We use a set of automatic evaluation metrics to assess the quality of translation models trained with data filtered by our method and data filtered with OpusFilter‘s default parameters. The trained models cover English-German and English-Ukrainian in both directions. The proposed method outperforms the default parameters in all translation directions for almost all evaluation metrics.</abstract>
<identifier type="citekey">aulamo-etal-2023-unsupervised</identifier>
<location>
<url>https://aclanthology.org/2023.eamt-1.4/</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>31</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Feature Selection for Effective Parallel Corpus Filtering
%A Aulamo, Mikko
%A de Gibert, Ona
%A Virpioja, Sami
%A Tiedemann, Jörg
%Y Nurminen, Mary
%Y Brenner, Judith
%Y Koponen, Maarit
%Y Latomaa, Sirkku
%Y Mikhailov, Mikhail
%Y Schierl, Frederike
%Y Ranasinghe, Tharindu
%Y Vanmassenhove, Eva
%Y Vidal, Sergi Alvarez
%Y Aranberri, Nora
%Y Nunziatini, Mara
%Y Escartín, Carla Parra
%Y Forcada, Mikel
%Y Popovic, Maja
%Y Scarton, Carolina
%Y Moniz, Helena
%S Proceedings of the 24th Annual Conference of the European Association for Machine Translation
%D 2023
%8 June
%I European Association for Machine Translation
%C Tampere, Finland
%F aulamo-etal-2023-unsupervised
%X This work presents an unsupervised method of selecting filters and threshold values for the OpusFilter parallel corpus cleaning toolbox. The method clusters sentence pairs into noisy and clean categories and uses the features of the noisy cluster center as filtering parameters. Our approach utilizes feature importance analysis to disregard filters that do not differentiate between clean and noisy data. A randomly sampled subset of a given corpus is used for filter selection and ineffective filters are not run for the full corpus. We use a set of automatic evaluation metrics to assess the quality of translation models trained with data filtered by our method and data filtered with OpusFilter‘s default parameters. The trained models cover English-German and English-Ukrainian in both directions. The proposed method outperforms the default parameters in all translation directions for almost all evaluation metrics.
%U https://aclanthology.org/2023.eamt-1.4/
%P 31-38
Markdown (Informal)
[Unsupervised Feature Selection for Effective Parallel Corpus Filtering](https://aclanthology.org/2023.eamt-1.4/) (Aulamo et al., EAMT 2023)
ACL