@inproceedings{luo-etal-2014-study,
title = "A Study on Expert Sourcing Enterprise Question Collection and Classification",
author = "Luo, Yuan and
Boucher, Thomas and
Oral, Tolga and
Osofsky, David and
Weber, Sara",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/25_Paper.pdf",
pages = "181--188",
abstract = "Large enterprises, such as IBM, accumulate petabytes of free-text data within their organizations. To mine this big data, a critical ability is to enable meaningful question answering beyond keywords search. In this paper, we present a study on the characteristics and classification of IBM sales questions. The characteristics are analyzed both semantically and syntactically, from where a question classification guideline evolves. We adopted an enterprise level expert sourcing approach to gather questions, annotate questions based on the guideline and manage the quality of annotations via enhanced inter-annotator agreement analysis. We developed a question feature extraction system and experimented with rule-based, statistical and hybrid question classifiers. We share our annotated corpus of questions and report our experimental results. Statistical classifiers separately based on n-grams and hand-crafted rule features give reasonable macro-f1 scores at 61.7{\%} and 63.1{\%} respectively. Rule based classifier gives a macro-f1 at 77.1{\%}. The hybrid classifier with n-gram and rule features using a second guess model further improves the macro-f1 to 83.9{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2014-study">
<titleInfo>
<title>A Study on Expert Sourcing Enterprise Question Collection and Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Boucher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tolga</namePart>
<namePart type="family">Oral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Osofsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Weber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large enterprises, such as IBM, accumulate petabytes of free-text data within their organizations. To mine this big data, a critical ability is to enable meaningful question answering beyond keywords search. In this paper, we present a study on the characteristics and classification of IBM sales questions. The characteristics are analyzed both semantically and syntactically, from where a question classification guideline evolves. We adopted an enterprise level expert sourcing approach to gather questions, annotate questions based on the guideline and manage the quality of annotations via enhanced inter-annotator agreement analysis. We developed a question feature extraction system and experimented with rule-based, statistical and hybrid question classifiers. We share our annotated corpus of questions and report our experimental results. Statistical classifiers separately based on n-grams and hand-crafted rule features give reasonable macro-f1 scores at 61.7% and 63.1% respectively. Rule based classifier gives a macro-f1 at 77.1%. The hybrid classifier with n-gram and rule features using a second guess model further improves the macro-f1 to 83.9%.</abstract>
<identifier type="citekey">luo-etal-2014-study</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/25_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>181</start>
<end>188</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Study on Expert Sourcing Enterprise Question Collection and Classification
%A Luo, Yuan
%A Boucher, Thomas
%A Oral, Tolga
%A Osofsky, David
%A Weber, Sara
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F luo-etal-2014-study
%X Large enterprises, such as IBM, accumulate petabytes of free-text data within their organizations. To mine this big data, a critical ability is to enable meaningful question answering beyond keywords search. In this paper, we present a study on the characteristics and classification of IBM sales questions. The characteristics are analyzed both semantically and syntactically, from where a question classification guideline evolves. We adopted an enterprise level expert sourcing approach to gather questions, annotate questions based on the guideline and manage the quality of annotations via enhanced inter-annotator agreement analysis. We developed a question feature extraction system and experimented with rule-based, statistical and hybrid question classifiers. We share our annotated corpus of questions and report our experimental results. Statistical classifiers separately based on n-grams and hand-crafted rule features give reasonable macro-f1 scores at 61.7% and 63.1% respectively. Rule based classifier gives a macro-f1 at 77.1%. The hybrid classifier with n-gram and rule features using a second guess model further improves the macro-f1 to 83.9%.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/25_Paper.pdf
%P 181-188
Markdown (Informal)
[A Study on Expert Sourcing Enterprise Question Collection and Classification](http://www.lrec-conf.org/proceedings/lrec2014/pdf/25_Paper.pdf) (Luo et al., LREC 2014)
ACL