@inproceedings{jungmaier-etal-2020-dirichlet,
title = "{D}irichlet-Smoothed Word Embeddings for Low-Resource Settings",
author = "Jungmaier, Jakob and
Kassner, Nora and
Roth, Benjamin",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.437",
pages = "3560--3565",
abstract = "Nowadays, classical count-based word embeddings using positive pointwise mutual information (PPMI) weighted co-occurrence matrices have been widely superseded by machine-learning-based methods like word2vec and GloVe. But these methods are usually applied using very large amounts of text data. In many cases, however, there is not much text data available, for example for specific domains or low-resource languages. This paper revisits PPMI by adding Dirichlet smoothing to correct its bias towards rare words. We evaluate on standard word similarity data sets and compare to word2vec and the recent state of the art for low-resource settings: Positive and Unlabeled (PU) Learning for word embeddings. The proposed method outperforms PU-Learning for low-resource settings and obtains competitive results for Maltese and Luxembourgish.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jungmaier-etal-2020-dirichlet">
<titleInfo>
<title>Dirichlet-Smoothed Word Embeddings for Low-Resource Settings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Jungmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kassner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Nowadays, classical count-based word embeddings using positive pointwise mutual information (PPMI) weighted co-occurrence matrices have been widely superseded by machine-learning-based methods like word2vec and GloVe. But these methods are usually applied using very large amounts of text data. In many cases, however, there is not much text data available, for example for specific domains or low-resource languages. This paper revisits PPMI by adding Dirichlet smoothing to correct its bias towards rare words. We evaluate on standard word similarity data sets and compare to word2vec and the recent state of the art for low-resource settings: Positive and Unlabeled (PU) Learning for word embeddings. The proposed method outperforms PU-Learning for low-resource settings and obtains competitive results for Maltese and Luxembourgish.</abstract>
<identifier type="citekey">jungmaier-etal-2020-dirichlet</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.437</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3560</start>
<end>3565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dirichlet-Smoothed Word Embeddings for Low-Resource Settings
%A Jungmaier, Jakob
%A Kassner, Nora
%A Roth, Benjamin
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F jungmaier-etal-2020-dirichlet
%X Nowadays, classical count-based word embeddings using positive pointwise mutual information (PPMI) weighted co-occurrence matrices have been widely superseded by machine-learning-based methods like word2vec and GloVe. But these methods are usually applied using very large amounts of text data. In many cases, however, there is not much text data available, for example for specific domains or low-resource languages. This paper revisits PPMI by adding Dirichlet smoothing to correct its bias towards rare words. We evaluate on standard word similarity data sets and compare to word2vec and the recent state of the art for low-resource settings: Positive and Unlabeled (PU) Learning for word embeddings. The proposed method outperforms PU-Learning for low-resource settings and obtains competitive results for Maltese and Luxembourgish.
%U https://aclanthology.org/2020.lrec-1.437
%P 3560-3565
Markdown (Informal)
[Dirichlet-Smoothed Word Embeddings for Low-Resource Settings](https://aclanthology.org/2020.lrec-1.437) (Jungmaier et al., LREC 2020)
ACL