@inproceedings{salawa-etal-2019-learn,
title = "Whom to Learn From? Graph- vs. Text-based Word Embeddings",
author = "Salawa, Ma{\l}gorzata and
Branco, Ant{\'o}nio and
Branco, Ruben and
Ant{\'o}nio Rodrigues, Jo{\~a}o and
Saedi, Chakaveh",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/R19-1120",
doi = "10.26615/978-954-452-056-4_120",
pages = "1041--1051",
abstract = "Vectorial representations of meaning can be supported by empirical data from diverse sources and obtained with diverse embedding approaches. This paper aims at screening this experimental space and reports on an assessment of word embeddings supported (i) by data in raw texts vs. in lexical graphs, (ii) by lexical information encoded in association- vs. inference-based graphs, and obtained (iii) by edge reconstruction- vs. matrix factorisation vs. random walk-based graph embedding methods. The results observed with these experiments indicate that the best solutions with graph-based word embeddings are very competitive, consistently outperforming mainstream text-based ones.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salawa-etal-2019-learn">
<titleInfo>
<title>Whom to Learn From? Graph- vs. Text-based Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Małgorzata</namePart>
<namePart type="family">Salawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">António</namePart>
<namePart type="family">Branco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruben</namePart>
<namePart type="family">Branco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">António Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chakaveh</namePart>
<namePart type="family">Saedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Vectorial representations of meaning can be supported by empirical data from diverse sources and obtained with diverse embedding approaches. This paper aims at screening this experimental space and reports on an assessment of word embeddings supported (i) by data in raw texts vs. in lexical graphs, (ii) by lexical information encoded in association- vs. inference-based graphs, and obtained (iii) by edge reconstruction- vs. matrix factorisation vs. random walk-based graph embedding methods. The results observed with these experiments indicate that the best solutions with graph-based word embeddings are very competitive, consistently outperforming mainstream text-based ones.</abstract>
<identifier type="citekey">salawa-etal-2019-learn</identifier>
<identifier type="doi">10.26615/978-954-452-056-4_120</identifier>
<location>
<url>https://aclanthology.org/R19-1120</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>1041</start>
<end>1051</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Whom to Learn From? Graph- vs. Text-based Word Embeddings
%A Salawa, Małgorzata
%A Branco, António
%A Branco, Ruben
%A António Rodrigues, João
%A Saedi, Chakaveh
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F salawa-etal-2019-learn
%X Vectorial representations of meaning can be supported by empirical data from diverse sources and obtained with diverse embedding approaches. This paper aims at screening this experimental space and reports on an assessment of word embeddings supported (i) by data in raw texts vs. in lexical graphs, (ii) by lexical information encoded in association- vs. inference-based graphs, and obtained (iii) by edge reconstruction- vs. matrix factorisation vs. random walk-based graph embedding methods. The results observed with these experiments indicate that the best solutions with graph-based word embeddings are very competitive, consistently outperforming mainstream text-based ones.
%R 10.26615/978-954-452-056-4_120
%U https://aclanthology.org/R19-1120
%U https://doi.org/10.26615/978-954-452-056-4_120
%P 1041-1051
Markdown (Informal)
[Whom to Learn From? Graph- vs. Text-based Word Embeddings](https://aclanthology.org/R19-1120) (Salawa et al., RANLP 2019)
ACL
- Małgorzata Salawa, António Branco, Ruben Branco, João António Rodrigues, and Chakaveh Saedi. 2019. Whom to Learn From? Graph- vs. Text-based Word Embeddings. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1041–1051, Varna, Bulgaria. INCOMA Ltd..