@inproceedings{kurfali-ostling-2019-noisy,
title = "Noisy Parallel Corpus Filtering through Projected Word Embeddings",
author = {Kurfal{\i}, Murathan and
{\"O}stling, Robert},
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/W19-5438",
doi = "10.18653/v1/W19-5438",
pages = "277--281",
abstract = "We present a very simple method for parallel text cleaning of low-resource languages, based on projection of word embeddings trained on large monolingual corpora in high-resource languages. In spite of its simplicity, we approach the strong baseline system in the downstream machine translation evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kurfali-ostling-2019-noisy">
<titleInfo>
<title>Noisy Parallel Corpus Filtering through Projected Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Murathan</namePart>
<namePart type="family">Kurfalı</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Östling</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 present a very simple method for parallel text cleaning of low-resource languages, based on projection of word embeddings trained on large monolingual corpora in high-resource languages. In spite of its simplicity, we approach the strong baseline system in the downstream machine translation evaluation.</abstract>
<identifier type="citekey">kurfali-ostling-2019-noisy</identifier>
<identifier type="doi">10.18653/v1/W19-5438</identifier>
<location>
<url>https://aclanthology.org/W19-5438</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>277</start>
<end>281</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Noisy Parallel Corpus Filtering through Projected Word Embeddings
%A Kurfalı, Murathan
%A Östling, Robert
%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 kurfali-ostling-2019-noisy
%X We present a very simple method for parallel text cleaning of low-resource languages, based on projection of word embeddings trained on large monolingual corpora in high-resource languages. In spite of its simplicity, we approach the strong baseline system in the downstream machine translation evaluation.
%R 10.18653/v1/W19-5438
%U https://aclanthology.org/W19-5438
%U https://doi.org/10.18653/v1/W19-5438
%P 277-281
Markdown (Informal)
[Noisy Parallel Corpus Filtering through Projected Word Embeddings](https://aclanthology.org/W19-5438) (Kurfalı & Östling, 2019)
ACL