@inproceedings{parcheta-etal-2019-filtering,
title = "Filtering of Noisy Parallel Corpora Based on Hypothesis Generation",
author = "Parcheta, Zuzanna and
Sanchis-Trilles, Germ{\'a}n and
Casacuberta, Francisco",
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/W19-5439/",
doi = "10.18653/v1/W19-5439",
pages = "282--288",
abstract = "The filtering task of noisy parallel corpora in WMT2019 aims to challenge participants to create filtering methods to be useful for training machine translation systems. In this work, we introduce a noisy parallel corpora filtering system based on generating hypotheses by means of a translation model. We train translation models in both language pairs: Nepali{--}English and Sinhala{--}English using provided parallel corpora. We select the training subset for three language pairs (Nepali, Sinhala and Hindi to English) jointly using bilingual cross-entropy selection to create the best possible translation model for both language pairs. Once the translation models are trained, we translate the noisy corpora and generate a hypothesis for each sentence pair. We compute the smoothed BLEU score between the target sentence and generated hypothesis. In addition, we apply several rules to discard very noisy or inadequate sentences which can lower the translation score. These heuristics are based on sentence length, source and target similarity and source language detection. We compare our results with the baseline published on the shared task website, which uses the Zipporah model, over which we achieve significant improvements in one of the conditions in the shared task. The designed filtering system is domain independent and all experiments are conducted using neural machine translation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parcheta-etal-2019-filtering">
<titleInfo>
<title>Filtering of Noisy Parallel Corpora Based on Hypothesis Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zuzanna</namePart>
<namePart type="family">Parcheta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Germán</namePart>
<namePart type="family">Sanchis-Trilles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Casacuberta</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>The filtering task of noisy parallel corpora in WMT2019 aims to challenge participants to create filtering methods to be useful for training machine translation systems. In this work, we introduce a noisy parallel corpora filtering system based on generating hypotheses by means of a translation model. We train translation models in both language pairs: Nepali–English and Sinhala–English using provided parallel corpora. We select the training subset for three language pairs (Nepali, Sinhala and Hindi to English) jointly using bilingual cross-entropy selection to create the best possible translation model for both language pairs. Once the translation models are trained, we translate the noisy corpora and generate a hypothesis for each sentence pair. We compute the smoothed BLEU score between the target sentence and generated hypothesis. In addition, we apply several rules to discard very noisy or inadequate sentences which can lower the translation score. These heuristics are based on sentence length, source and target similarity and source language detection. We compare our results with the baseline published on the shared task website, which uses the Zipporah model, over which we achieve significant improvements in one of the conditions in the shared task. The designed filtering system is domain independent and all experiments are conducted using neural machine translation.</abstract>
<identifier type="citekey">parcheta-etal-2019-filtering</identifier>
<identifier type="doi">10.18653/v1/W19-5439</identifier>
<location>
<url>https://aclanthology.org/W19-5439/</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>282</start>
<end>288</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Filtering of Noisy Parallel Corpora Based on Hypothesis Generation
%A Parcheta, Zuzanna
%A Sanchis-Trilles, Germán
%A Casacuberta, Francisco
%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 parcheta-etal-2019-filtering
%X The filtering task of noisy parallel corpora in WMT2019 aims to challenge participants to create filtering methods to be useful for training machine translation systems. In this work, we introduce a noisy parallel corpora filtering system based on generating hypotheses by means of a translation model. We train translation models in both language pairs: Nepali–English and Sinhala–English using provided parallel corpora. We select the training subset for three language pairs (Nepali, Sinhala and Hindi to English) jointly using bilingual cross-entropy selection to create the best possible translation model for both language pairs. Once the translation models are trained, we translate the noisy corpora and generate a hypothesis for each sentence pair. We compute the smoothed BLEU score between the target sentence and generated hypothesis. In addition, we apply several rules to discard very noisy or inadequate sentences which can lower the translation score. These heuristics are based on sentence length, source and target similarity and source language detection. We compare our results with the baseline published on the shared task website, which uses the Zipporah model, over which we achieve significant improvements in one of the conditions in the shared task. The designed filtering system is domain independent and all experiments are conducted using neural machine translation.
%R 10.18653/v1/W19-5439
%U https://aclanthology.org/W19-5439/
%U https://doi.org/10.18653/v1/W19-5439
%P 282-288
Markdown (Informal)
[Filtering of Noisy Parallel Corpora Based on Hypothesis Generation](https://aclanthology.org/W19-5439/) (Parcheta et al., WMT 2019)
ACL