@inproceedings{schwenk-etal-2021-wikimatrix,
title = "{W}iki{M}atrix: Mining 135{M} Parallel Sentences in 1620 Language Pairs from {W}ikipedia",
author = "Schwenk, Holger and
Chaudhary, Vishrav and
Sun, Shuo and
Gong, Hongyu and
Guzm{\'a}n, Francisco",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.115",
doi = "10.18653/v1/2021.eacl-main.115",
pages = "1351--1361",
abstract = "We present an approach based on multilingual sentence embeddings to automatically extract parallel sentences from the content of Wikipedia articles in 96 languages, including several dialects or low-resource languages. We do not limit the extraction process to alignments with English, but we systematically consider all possible language pairs. In total, we are able to extract 135M parallel sentences for 16720 different language pairs, out of which only 34M are aligned with English. This corpus is freely available. To get an indication on the quality of the extracted bitexts, we train neural MT baseline systems on the mined data only for 1886 languages pairs, and evaluate them on the TED corpus, achieving strong BLEU scores for many language pairs. The WikiMatrix bitexts seem to be particularly interesting to train MT systems between distant languages without the need to pivot through English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schwenk-etal-2021-wikimatrix">
<titleInfo>
<title>WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Holger</namePart>
<namePart type="family">Schwenk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishrav</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Guzmán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present an approach based on multilingual sentence embeddings to automatically extract parallel sentences from the content of Wikipedia articles in 96 languages, including several dialects or low-resource languages. We do not limit the extraction process to alignments with English, but we systematically consider all possible language pairs. In total, we are able to extract 135M parallel sentences for 16720 different language pairs, out of which only 34M are aligned with English. This corpus is freely available. To get an indication on the quality of the extracted bitexts, we train neural MT baseline systems on the mined data only for 1886 languages pairs, and evaluate them on the TED corpus, achieving strong BLEU scores for many language pairs. The WikiMatrix bitexts seem to be particularly interesting to train MT systems between distant languages without the need to pivot through English.</abstract>
<identifier type="citekey">schwenk-etal-2021-wikimatrix</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.115</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.115</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1351</start>
<end>1361</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia
%A Schwenk, Holger
%A Chaudhary, Vishrav
%A Sun, Shuo
%A Gong, Hongyu
%A Guzmán, Francisco
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F schwenk-etal-2021-wikimatrix
%X We present an approach based on multilingual sentence embeddings to automatically extract parallel sentences from the content of Wikipedia articles in 96 languages, including several dialects or low-resource languages. We do not limit the extraction process to alignments with English, but we systematically consider all possible language pairs. In total, we are able to extract 135M parallel sentences for 16720 different language pairs, out of which only 34M are aligned with English. This corpus is freely available. To get an indication on the quality of the extracted bitexts, we train neural MT baseline systems on the mined data only for 1886 languages pairs, and evaluate them on the TED corpus, achieving strong BLEU scores for many language pairs. The WikiMatrix bitexts seem to be particularly interesting to train MT systems between distant languages without the need to pivot through English.
%R 10.18653/v1/2021.eacl-main.115
%U https://aclanthology.org/2021.eacl-main.115
%U https://doi.org/10.18653/v1/2021.eacl-main.115
%P 1351-1361
Markdown (Informal)
[WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia](https://aclanthology.org/2021.eacl-main.115) (Schwenk et al., EACL 2021)
ACL