@inproceedings{izbicki-2022-aligning,
title = "Aligning Word Vectors on Low-Resource Languages with {W}iktionary",
author = "Izbicki, Mike",
editor = "Ojha, Atul Kr. and
Liu, Chao-Hong and
Vylomova, Ekaterina and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Pirinen, Tommi A and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.loresmt-1.14/",
pages = "107--117",
abstract = "Aligned word embeddings have become a popular technique for low-resource natural language processing. Most existing evaluation datasets are generated automatically from machine translations systems, so they have many errors and exist only for high-resource languages. We introduce the Wiktionary bilingual lexicon collection, which provides high-quality human annotated translations for words in 298 languages to English. We use these lexicons to train and evaluate the largest published collection of aligned word embeddings on 157 different languages. All of our code and data is publicly available at \url{https://github.com/mikeizbicki/wiktionary_bli}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="izbicki-2022-aligning">
<titleInfo>
<title>Aligning Word Vectors on Low-Resource Languages with Wiktionary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Izbicki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Aligned word embeddings have become a popular technique for low-resource natural language processing. Most existing evaluation datasets are generated automatically from machine translations systems, so they have many errors and exist only for high-resource languages. We introduce the Wiktionary bilingual lexicon collection, which provides high-quality human annotated translations for words in 298 languages to English. We use these lexicons to train and evaluate the largest published collection of aligned word embeddings on 157 different languages. All of our code and data is publicly available at https://github.com/mikeizbicki/wiktionary_bli.</abstract>
<identifier type="citekey">izbicki-2022-aligning</identifier>
<location>
<url>https://aclanthology.org/2022.loresmt-1.14/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>107</start>
<end>117</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning Word Vectors on Low-Resource Languages with Wiktionary
%A Izbicki, Mike
%Y Ojha, Atul Kr.
%Y Liu, Chao-Hong
%Y Vylomova, Ekaterina
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Pirinen, Tommi A.
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F izbicki-2022-aligning
%X Aligned word embeddings have become a popular technique for low-resource natural language processing. Most existing evaluation datasets are generated automatically from machine translations systems, so they have many errors and exist only for high-resource languages. We introduce the Wiktionary bilingual lexicon collection, which provides high-quality human annotated translations for words in 298 languages to English. We use these lexicons to train and evaluate the largest published collection of aligned word embeddings on 157 different languages. All of our code and data is publicly available at https://github.com/mikeizbicki/wiktionary_bli.
%U https://aclanthology.org/2022.loresmt-1.14/
%P 107-117
Markdown (Informal)
[Aligning Word Vectors on Low-Resource Languages with Wiktionary](https://aclanthology.org/2022.loresmt-1.14/) (Izbicki, LoResMT 2022)
ACL