@inproceedings{yamada-etal-2020-wikipedia2vec,
title = "{W}ikipedia2{V}ec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from {W}ikipedia",
author = "Yamada, Ikuya and
Asai, Akari and
Sakuma, Jin and
Shindo, Hiroyuki and
Takeda, Hideaki and
Takefuji, Yoshiyasu and
Matsumoto, Yuji",
editor = "Liu, Qun and
Schlangen, David",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-demos.4",
doi = "10.18653/v1/2020.emnlp-demos.4",
pages = "23--30",
abstract = "The embeddings of entities in a large knowledge base (e.g., Wikipedia) are highly beneficial for solving various natural language tasks that involve real world knowledge. In this paper, we present Wikipedia2Vec, a Python-based open-source tool for learning the embeddings of words and entities from Wikipedia. The proposed tool enables users to learn the embeddings efficiently by issuing a single command with a Wikipedia dump file as an argument. We also introduce a web-based demonstration of our tool that allows users to visualize and explore the learned embeddings. In our experiments, our tool achieved a state-of-the-art result on the KORE entity relatedness dataset, and competitive results on various standard benchmark datasets. Furthermore, our tool has been used as a key component in various recent studies. We publicize the source code, demonstration, and the pretrained embeddings for 12 languages at \url{https://wikipedia2vec.github.io/}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yamada-etal-2020-wikipedia2vec">
<titleInfo>
<title>Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ikuya</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akari</namePart>
<namePart type="family">Asai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Sakuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroyuki</namePart>
<namePart type="family">Shindo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideaki</namePart>
<namePart type="family">Takeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshiyasu</namePart>
<namePart type="family">Takefuji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</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>The embeddings of entities in a large knowledge base (e.g., Wikipedia) are highly beneficial for solving various natural language tasks that involve real world knowledge. In this paper, we present Wikipedia2Vec, a Python-based open-source tool for learning the embeddings of words and entities from Wikipedia. The proposed tool enables users to learn the embeddings efficiently by issuing a single command with a Wikipedia dump file as an argument. We also introduce a web-based demonstration of our tool that allows users to visualize and explore the learned embeddings. In our experiments, our tool achieved a state-of-the-art result on the KORE entity relatedness dataset, and competitive results on various standard benchmark datasets. Furthermore, our tool has been used as a key component in various recent studies. We publicize the source code, demonstration, and the pretrained embeddings for 12 languages at https://wikipedia2vec.github.io/.</abstract>
<identifier type="citekey">yamada-etal-2020-wikipedia2vec</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-demos.4</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-demos.4</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>23</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia
%A Yamada, Ikuya
%A Asai, Akari
%A Sakuma, Jin
%A Shindo, Hiroyuki
%A Takeda, Hideaki
%A Takefuji, Yoshiyasu
%A Matsumoto, Yuji
%Y Liu, Qun
%Y Schlangen, David
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2020
%8 October
%I Association for Computational Linguistics
%C Online
%F yamada-etal-2020-wikipedia2vec
%X The embeddings of entities in a large knowledge base (e.g., Wikipedia) are highly beneficial for solving various natural language tasks that involve real world knowledge. In this paper, we present Wikipedia2Vec, a Python-based open-source tool for learning the embeddings of words and entities from Wikipedia. The proposed tool enables users to learn the embeddings efficiently by issuing a single command with a Wikipedia dump file as an argument. We also introduce a web-based demonstration of our tool that allows users to visualize and explore the learned embeddings. In our experiments, our tool achieved a state-of-the-art result on the KORE entity relatedness dataset, and competitive results on various standard benchmark datasets. Furthermore, our tool has been used as a key component in various recent studies. We publicize the source code, demonstration, and the pretrained embeddings for 12 languages at https://wikipedia2vec.github.io/.
%R 10.18653/v1/2020.emnlp-demos.4
%U https://aclanthology.org/2020.emnlp-demos.4
%U https://doi.org/10.18653/v1/2020.emnlp-demos.4
%P 23-30
Markdown (Informal)
[Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia](https://aclanthology.org/2020.emnlp-demos.4) (Yamada et al., EMNLP 2020)
ACL