@inproceedings{axelrod-etal-2019-dual,
title = "Dual Monolingual Cross-Entropy Delta Filtering of Noisy Parallel Data",
author = "Axelrod, Amittai and
Kumar, Anish and
Sloto, Steve",
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/W19-5433",
doi = "10.18653/v1/W19-5433",
pages = "245--251",
abstract = "We introduce a purely monolingual approach to filtering for parallel data from a noisy corpus in a low-resource scenario. Our work is inspired by Junczysdowmunt:2018, but we relax the requirements to allow for cases where no parallel data is available. Our primary contribution is a dual monolingual cross-entropy delta criterion modified from Cynical data selection Axelrod:2017, and is competitive (within 1.8 BLEU) with the best bilingual filtering method when used to train SMT systems. Our approach is featherweight, and runs end-to-end on a standard laptop in three hours.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="axelrod-etal-2019-dual">
<titleInfo>
<title>Dual Monolingual Cross-Entropy Delta Filtering of Noisy Parallel Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amittai</namePart>
<namePart type="family">Axelrod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anish</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Sloto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a purely monolingual approach to filtering for parallel data from a noisy corpus in a low-resource scenario. Our work is inspired by Junczysdowmunt:2018, but we relax the requirements to allow for cases where no parallel data is available. Our primary contribution is a dual monolingual cross-entropy delta criterion modified from Cynical data selection Axelrod:2017, and is competitive (within 1.8 BLEU) with the best bilingual filtering method when used to train SMT systems. Our approach is featherweight, and runs end-to-end on a standard laptop in three hours.</abstract>
<identifier type="citekey">axelrod-etal-2019-dual</identifier>
<identifier type="doi">10.18653/v1/W19-5433</identifier>
<location>
<url>https://aclanthology.org/W19-5433</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>245</start>
<end>251</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dual Monolingual Cross-Entropy Delta Filtering of Noisy Parallel Data
%A Axelrod, Amittai
%A Kumar, Anish
%A Sloto, Steve
%S Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F axelrod-etal-2019-dual
%X We introduce a purely monolingual approach to filtering for parallel data from a noisy corpus in a low-resource scenario. Our work is inspired by Junczysdowmunt:2018, but we relax the requirements to allow for cases where no parallel data is available. Our primary contribution is a dual monolingual cross-entropy delta criterion modified from Cynical data selection Axelrod:2017, and is competitive (within 1.8 BLEU) with the best bilingual filtering method when used to train SMT systems. Our approach is featherweight, and runs end-to-end on a standard laptop in three hours.
%R 10.18653/v1/W19-5433
%U https://aclanthology.org/W19-5433
%U https://doi.org/10.18653/v1/W19-5433
%P 245-251
Markdown (Informal)
[Dual Monolingual Cross-Entropy Delta Filtering of Noisy Parallel Data](https://aclanthology.org/W19-5433) (Axelrod et al., 2019)
ACL