@inproceedings{polifroni-etal-2010-bootstrapping,
title = "Bootstrapping Named Entity Extraction for the Creation of Mobile Services",
author = "Polifroni, Joseph and
Kiss, Imre and
Adler, Mark",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/280_Paper.pdf",
abstract = "As users become more accustomed to using their mobile devices to organize and schedule their lives, there is more of a demand for applications that can make that process easier. Automatic speech recognition technology has already been developed to enable essentially unlimited vocabulary in a mobile setting. Understanding the words that are spoken is the next challenge. In this paper, we describe efforts to develop a dataset and classifier to recognize named entities in speech. Using sets of both real and simulated data, in conjunction with a very large set of real named entities, we created a challenging corpus of training and test data. We use these data to develop a classifier to identify names and locations on a word-by-word basis. In this paper, we describe the process of creating the data and determining a set of features to use for named entity recognition. We report on our classification performance on these data, as well as point to future work in improving all aspects of the system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="polifroni-etal-2010-bootstrapping">
<titleInfo>
<title>Bootstrapping Named Entity Extraction for the Creation of Mobile Services</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Polifroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imre</namePart>
<namePart type="family">Kiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Adler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As users become more accustomed to using their mobile devices to organize and schedule their lives, there is more of a demand for applications that can make that process easier. Automatic speech recognition technology has already been developed to enable essentially unlimited vocabulary in a mobile setting. Understanding the words that are spoken is the next challenge. In this paper, we describe efforts to develop a dataset and classifier to recognize named entities in speech. Using sets of both real and simulated data, in conjunction with a very large set of real named entities, we created a challenging corpus of training and test data. We use these data to develop a classifier to identify names and locations on a word-by-word basis. In this paper, we describe the process of creating the data and determining a set of features to use for named entity recognition. We report on our classification performance on these data, as well as point to future work in improving all aspects of the system.</abstract>
<identifier type="citekey">polifroni-etal-2010-bootstrapping</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/280_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bootstrapping Named Entity Extraction for the Creation of Mobile Services
%A Polifroni, Joseph
%A Kiss, Imre
%A Adler, Mark
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F polifroni-etal-2010-bootstrapping
%X As users become more accustomed to using their mobile devices to organize and schedule their lives, there is more of a demand for applications that can make that process easier. Automatic speech recognition technology has already been developed to enable essentially unlimited vocabulary in a mobile setting. Understanding the words that are spoken is the next challenge. In this paper, we describe efforts to develop a dataset and classifier to recognize named entities in speech. Using sets of both real and simulated data, in conjunction with a very large set of real named entities, we created a challenging corpus of training and test data. We use these data to develop a classifier to identify names and locations on a word-by-word basis. In this paper, we describe the process of creating the data and determining a set of features to use for named entity recognition. We report on our classification performance on these data, as well as point to future work in improving all aspects of the system.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/280_Paper.pdf
Markdown (Informal)
[Bootstrapping Named Entity Extraction for the Creation of Mobile Services](http://www.lrec-conf.org/proceedings/lrec2010/pdf/280_Paper.pdf) (Polifroni et al., LREC 2010)
ACL