@inproceedings{korkontzelos-etal-2016-ensemble,
title = "Ensemble Classification of Grants using {LDA}-based Features",
author = "Korkontzelos, Yannis and
Thomas, Beverley and
Miwa, Makoto and
Ananiadou, Sophia",
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/L16-1205/",
pages = "1288--1294",
abstract = "Classifying research grants into useful categories is a vital task for a funding body to give structure to the portfolio for analysis, informing strategic planning and decision-making. Automating this classification process would save time and effort, providing the accuracy of the classifications is maintained. We employ five classification models to classify a set of BBSRC-funded research grants in 21 research topics based on unigrams, technical terms and Latent Dirichlet Allocation models. To boost precision, we investigate methods for combining their predictions into five aggregate classifiers. Evaluation confirmed that ensemble classification models lead to higher precision. It was observed that there is not a single best-performing aggregate method for all research topics. Instead, the best-performing method for a research topic depends on the number of positive training instances available for this topic. Subject matter experts considered the predictions of aggregate models to correct erroneous or incomplete manual assignments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="korkontzelos-etal-2016-ensemble">
<titleInfo>
<title>Ensemble Classification of Grants using LDA-based Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yannis</namePart>
<namePart type="family">Korkontzelos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beverley</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</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>Classifying research grants into useful categories is a vital task for a funding body to give structure to the portfolio for analysis, informing strategic planning and decision-making. Automating this classification process would save time and effort, providing the accuracy of the classifications is maintained. We employ five classification models to classify a set of BBSRC-funded research grants in 21 research topics based on unigrams, technical terms and Latent Dirichlet Allocation models. To boost precision, we investigate methods for combining their predictions into five aggregate classifiers. Evaluation confirmed that ensemble classification models lead to higher precision. It was observed that there is not a single best-performing aggregate method for all research topics. Instead, the best-performing method for a research topic depends on the number of positive training instances available for this topic. Subject matter experts considered the predictions of aggregate models to correct erroneous or incomplete manual assignments.</abstract>
<identifier type="citekey">korkontzelos-etal-2016-ensemble</identifier>
<location>
<url>https://aclanthology.org/L16-1205/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1288</start>
<end>1294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ensemble Classification of Grants using LDA-based Features
%A Korkontzelos, Yannis
%A Thomas, Beverley
%A Miwa, Makoto
%A Ananiadou, Sophia
%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 korkontzelos-etal-2016-ensemble
%X Classifying research grants into useful categories is a vital task for a funding body to give structure to the portfolio for analysis, informing strategic planning and decision-making. Automating this classification process would save time and effort, providing the accuracy of the classifications is maintained. We employ five classification models to classify a set of BBSRC-funded research grants in 21 research topics based on unigrams, technical terms and Latent Dirichlet Allocation models. To boost precision, we investigate methods for combining their predictions into five aggregate classifiers. Evaluation confirmed that ensemble classification models lead to higher precision. It was observed that there is not a single best-performing aggregate method for all research topics. Instead, the best-performing method for a research topic depends on the number of positive training instances available for this topic. Subject matter experts considered the predictions of aggregate models to correct erroneous or incomplete manual assignments.
%U https://aclanthology.org/L16-1205/
%P 1288-1294
Markdown (Informal)
[Ensemble Classification of Grants using LDA-based Features](https://aclanthology.org/L16-1205/) (Korkontzelos et al., LREC 2016)
ACL
- Yannis Korkontzelos, Beverley Thomas, Makoto Miwa, and Sophia Ananiadou. 2016. Ensemble Classification of Grants using LDA-based Features. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1288–1294, Portorož, Slovenia. European Language Resources Association (ELRA).