@inproceedings{mencia-etal-2016-medical,
title = "Medical Concept Embeddings via Labeled Background Corpora",
author = "Menc{\'\i}a, Eneldo Loza and
de Melo, Gerard and
Nam, Jinseok",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1733",
pages = "4629--4636",
abstract = "In recent years, we have seen an increasing amount of interest in low-dimensional vector representations of words. Among other things, these facilitate computing word similarity and relatedness scores. The most well-known example of algorithms to produce representations of this sort are the word2vec approaches. In this paper, we investigate a new model to induce such vector spaces for medical concepts, based on a joint objective that exploits not only word co-occurrences but also manually labeled documents, as available from sources such as PubMed. Our extensive experimental analysis shows that our embeddings lead to significantly higher correlations with human similarity and relatedness assessments than previous work. Due to the simplicity and versatility of vector representations, these findings suggest that our resource can easily be used as a drop-in replacement to improve any systems relying on medical concept similarity measures.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mencia-etal-2016-medical">
<titleInfo>
<title>Medical Concept Embeddings via Labeled Background Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eneldo</namePart>
<namePart type="given">Loza</namePart>
<namePart type="family">Mencía</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerard</namePart>
<namePart type="family">de Melo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinseok</namePart>
<namePart type="family">Nam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, we have seen an increasing amount of interest in low-dimensional vector representations of words. Among other things, these facilitate computing word similarity and relatedness scores. The most well-known example of algorithms to produce representations of this sort are the word2vec approaches. In this paper, we investigate a new model to induce such vector spaces for medical concepts, based on a joint objective that exploits not only word co-occurrences but also manually labeled documents, as available from sources such as PubMed. Our extensive experimental analysis shows that our embeddings lead to significantly higher correlations with human similarity and relatedness assessments than previous work. Due to the simplicity and versatility of vector representations, these findings suggest that our resource can easily be used as a drop-in replacement to improve any systems relying on medical concept similarity measures.</abstract>
<identifier type="citekey">mencia-etal-2016-medical</identifier>
<location>
<url>https://aclanthology.org/L16-1733</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4629</start>
<end>4636</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Medical Concept Embeddings via Labeled Background Corpora
%A Mencía, Eneldo Loza
%A de Melo, Gerard
%A Nam, Jinseok
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F mencia-etal-2016-medical
%X In recent years, we have seen an increasing amount of interest in low-dimensional vector representations of words. Among other things, these facilitate computing word similarity and relatedness scores. The most well-known example of algorithms to produce representations of this sort are the word2vec approaches. In this paper, we investigate a new model to induce such vector spaces for medical concepts, based on a joint objective that exploits not only word co-occurrences but also manually labeled documents, as available from sources such as PubMed. Our extensive experimental analysis shows that our embeddings lead to significantly higher correlations with human similarity and relatedness assessments than previous work. Due to the simplicity and versatility of vector representations, these findings suggest that our resource can easily be used as a drop-in replacement to improve any systems relying on medical concept similarity measures.
%U https://aclanthology.org/L16-1733
%P 4629-4636
Markdown (Informal)
[Medical Concept Embeddings via Labeled Background Corpora](https://aclanthology.org/L16-1733) (Mencía et al., LREC 2016)
ACL
- Eneldo Loza Mencía, Gerard de Melo, and Jinseok Nam. 2016. Medical Concept Embeddings via Labeled Background Corpora. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4629–4636, Portorož, Slovenia. European Language Resources Association (ELRA).