Serveur d'exploration sur SGML

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

Comparing noun phrasing techniques for use with medical digital library tools

Identifieur interne : 001B81 ( Main/Exploration ); précédent : 001B80; suivant : 001B82

Comparing noun phrasing techniques for use with medical digital library tools

Auteurs : Kristin M. Tolle [États-Unis] ; Hsinchun Chen [États-Unis]

Source :

RBID : ISTEX:F89A78E6F114B4601DE09E6221D5DF8DC95B240F

English descriptors

Abstract

In an effort to assist medical researchers and professionals in accessing information necessary for their work, the A1 Lab at the University of Arizona is investigating the use of a natural language processing (NLP) technique called noun phrasing. The goal of this research is to determine whether noun phrasing could be a viable technique to include in medical information retrieval applications. Four noun phrase generation tools were evaluated as to their ability to isolate noun phrases from medical journal abstracts. Tests were conducted using the National Cancer Institute's CANCERLIT database. The NLP tools evaluated were Massachusetts Institute of Technology's (MIT's) Chopper, The University of Arizona's Automatic Indexer, Lingsoft's NPtool, and The University of Arizona's AZ Noun Phraser. In addition, the National Library of Medicine's SPECIALIST Lexicon was incorporated into two versions of the AZ Noun Phraser to be evaluated against the other tools as well as a nonaugmented version of the AZ Noun Phraser. Using the metrics relative subject recall and precision, our results show that, with the exception of Chopper, the phrasing tools were fairly comparable in recall and precision. It was also shown that augmenting the AZ Noun Phraser by including the SPECIALIST Lexicon from the National Library of Medicine resulted in improved recall and precision.

Url:
DOI: 10.1002/(SICI)1097-4571(2000)51:4<352::AID-ASI5>3.0.CO;2-8


Affiliations:


Links toward previous steps (curation, corpus...)


Le document en format XML

<record>
<TEI wicri:istexFullTextTei="biblStruct">
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en">Comparing noun phrasing techniques for use with medical digital library tools</title>
<author>
<name sortKey="Tolle, Kristin M" sort="Tolle, Kristin M" uniqKey="Tolle K" first="Kristin M." last="Tolle">Kristin M. Tolle</name>
</author>
<author>
<name sortKey="Chen, Hsinchun" sort="Chen, Hsinchun" uniqKey="Chen H" first="Hsinchun" last="Chen">Hsinchun Chen</name>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:F89A78E6F114B4601DE09E6221D5DF8DC95B240F</idno>
<date when="2000" year="2000">2000</date>
<idno type="doi">10.1002/(SICI)1097-4571(2000)51:4<352::AID-ASI5>3.0.CO;2-8</idno>
<idno type="url">https://api.istex.fr/ark:/67375/WNG-RRGVX20X-M/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">004096</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">004096</idno>
<idno type="wicri:Area/Istex/Curation">003300</idno>
<idno type="wicri:Area/Istex/Checkpoint">001A10</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">001A10</idno>
<idno type="wicri:doubleKey">0002-8231:2000:Tolle K:comparing:noun:phrasing</idno>
<idno type="wicri:Area/Main/Merge">001C25</idno>
<idno type="wicri:Area/Main/Curation">001B81</idno>
<idno type="wicri:Area/Main/Exploration">001B81</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title level="a" type="main" xml:lang="en">Comparing noun phrasing techniques for use with medical digital library tools</title>
<author>
<name sortKey="Tolle, Kristin M" sort="Tolle, Kristin M" uniqKey="Tolle K" first="Kristin M." last="Tolle">Kristin M. Tolle</name>
<affiliation wicri:level="1">
<country wicri:rule="url">États-Unis</country>
</affiliation>
<affiliation wicri:level="2">
<country xml:lang="fr">États-Unis</country>
<placeName>
<region type="state">Arizona</region>
</placeName>
<wicri:cityArea>Management Information Systems Department, University of Arizona, Tucson</wicri:cityArea>
</affiliation>
<affiliation wicri:level="1">
<country wicri:rule="url">États-Unis</country>
</affiliation>
</author>
<author>
<name sortKey="Chen, Hsinchun" sort="Chen, Hsinchun" uniqKey="Chen H" first="Hsinchun" last="Chen">Hsinchun Chen</name>
<affiliation wicri:level="2">
<country xml:lang="fr">États-Unis</country>
<placeName>
<region type="state">Arizona</region>
</placeName>
<wicri:cityArea>Management Information Systems Department, University of Arizona, Tucson</wicri:cityArea>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series>
<title level="j" type="main">Journal of the American Society for Information Science</title>
<title level="j" type="sub">Digital Libraries: Part 2</title>
<title level="j" type="alt">JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE</title>
<idno type="ISSN">0002-8231</idno>
<idno type="eISSN">1097-4571</idno>
<imprint>
<biblScope unit="vol">51</biblScope>
<biblScope unit="issue">4</biblScope>
<biblScope unit="page" from="352">352</biblScope>
<biblScope unit="page" to="370">370</biblScope>
<biblScope unit="page-count">19</biblScope>
<publisher>John Wiley & Sons, Inc.</publisher>
<pubPlace>New York</pubPlace>
<date type="published" when="2000">2000</date>
</imprint>
<idno type="ISSN">0002-8231</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt>
<idno type="ISSN">0002-8231</idno>
</seriesStmt>
</fileDesc>
<profileDesc>
<textClass>
<keywords scheme="Teeft" xml:lang="en">
<term>American society</term>
<term>Anick vaithyanathan</term>
<term>Annual symposium</term>
<term>Automatic indexing</term>
<term>Aznp</term>
<term>Boguraev</term>
<term>Boguraev pustejovski</term>
<term>Brill</term>
<term>Brill tagger</term>
<term>Brown corpus</term>
<term>Cambridge university press</term>
<term>Cancer research results</term>
<term>Cancerlit</term>
<term>Cancerlit collection</term>
<term>Chen</term>
<term>Chopper</term>
<term>Computational linguistics</term>
<term>Computer applications</term>
<term>Concept extraction</term>
<term>Concept space</term>
<term>Concept spaces</term>
<term>Current version</term>
<term>Data collections</term>
<term>Database</term>
<term>Detmer shortliffe</term>
<term>Different domains</term>
<term>Different phrases</term>
<term>Different techniques</term>
<term>Different versions</term>
<term>Digital libraries</term>
<term>Document collection</term>
<term>Document keywords</term>
<term>Document retrieval</term>
<term>Fewer phrases</term>
<term>Free text</term>
<term>Government reports</term>
<term>Great deal</term>
<term>High overlap</term>
<term>Human indexers</term>
<term>Human language technology</term>
<term>Hunting dogs</term>
<term>Indexer</term>
<term>Indexing</term>
<term>Information processing</term>
<term>Information producers</term>
<term>Information providers</term>
<term>Information retrieval</term>
<term>Information retrieval systems</term>
<term>Information science</term>
<term>Information seekers</term>
<term>Information sources</term>
<term>Interface</term>
<term>Interim noun phrases</term>
<term>Interim phrase generation tools</term>
<term>Interim phrases</term>
<term>Internet</term>
<term>Karlsson karttunen</term>
<term>Keyword</term>
<term>Keywords</term>
<term>Lexical</term>
<term>Lexical analysis</term>
<term>Lexical entries</term>
<term>Lexical knowledge</term>
<term>Lexical properties</term>
<term>Lexicon</term>
<term>Longest phrase</term>
<term>Longest phrase generation</term>
<term>Machine understanding group</term>
<term>Medical abstracts</term>
<term>Medical care</term>
<term>Medical domain</term>
<term>Medical goal</term>
<term>Medical information</term>
<term>Medical information retrieval</term>
<term>Medical journal abstracts</term>
<term>Medical professionals</term>
<term>Medical researchers</term>
<term>Medical terminology</term>
<term>Mesh terms</term>
<term>More phrases</term>
<term>National cancer institute</term>
<term>National library</term>
<term>Natural language</term>
<term>Natural language processing</term>
<term>Noun</term>
<term>Noun phrase</term>
<term>Noun phraser</term>
<term>Noun phraser noun phraser</term>
<term>Noun phraser versions</term>
<term>Noun phrasers</term>
<term>Noun phrases</term>
<term>Noun phrasing</term>
<term>Nptool</term>
<term>Nptool auto index</term>
<term>Other phrase generation techniques</term>
<term>Other techniques</term>
<term>Other tools</term>
<term>Overlap analysis</term>
<term>Patient record</term>
<term>Phrase</term>
<term>Phrase generation tools</term>
<term>Phrase output</term>
<term>Phraser</term>
<term>Phrasing</term>
<term>Phrasing tools</term>
<term>Precision comparison</term>
<term>Pustejovski</term>
<term>Query</term>
<term>Query expansion</term>
<term>Query formation</term>
<term>Relevant concepts</term>
<term>Relevant phrases</term>
<term>Research questions</term>
<term>Results show</term>
<term>Retrieval</term>
<term>Salton</term>
<term>Same document</term>
<term>Sample output</term>
<term>Schatz</term>
<term>Science alliance</term>
<term>Search engines</term>
<term>Semantic indexing</term>
<term>Semantic network</term>
<term>Semantic types</term>
<term>Sigir conference</term>
<term>Specialist lexicon</term>
<term>Statistical methods</term>
<term>Stochastic methods</term>
<term>Tagger</term>
<term>Test collection</term>
<term>Text corpora</term>
<term>Text documents</term>
<term>Textual data</term>
<term>Textual unit</term>
<term>Thesaurus</term>
<term>Total number</term>
<term>Training corpus</term>
<term>Umls</term>
<term>Umls knowledge sources</term>
<term>Unbiased estimates</term>
<term>Variance</term>
<term>Vector space representation</term>
<term>Vocabulary problem</term>
<term>Wall street journal</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en">In an effort to assist medical researchers and professionals in accessing information necessary for their work, the A1 Lab at the University of Arizona is investigating the use of a natural language processing (NLP) technique called noun phrasing. The goal of this research is to determine whether noun phrasing could be a viable technique to include in medical information retrieval applications. Four noun phrase generation tools were evaluated as to their ability to isolate noun phrases from medical journal abstracts. Tests were conducted using the National Cancer Institute's CANCERLIT database. The NLP tools evaluated were Massachusetts Institute of Technology's (MIT's) Chopper, The University of Arizona's Automatic Indexer, Lingsoft's NPtool, and The University of Arizona's AZ Noun Phraser. In addition, the National Library of Medicine's SPECIALIST Lexicon was incorporated into two versions of the AZ Noun Phraser to be evaluated against the other tools as well as a nonaugmented version of the AZ Noun Phraser. Using the metrics relative subject recall and precision, our results show that, with the exception of Chopper, the phrasing tools were fairly comparable in recall and precision. It was also shown that augmenting the AZ Noun Phraser by including the SPECIALIST Lexicon from the National Library of Medicine resulted in improved recall and precision.</div>
</front>
</TEI>
<affiliations>
<list>
<country>
<li>États-Unis</li>
</country>
<region>
<li>Arizona</li>
</region>
</list>
<tree>
<country name="États-Unis">
<noRegion>
<name sortKey="Tolle, Kristin M" sort="Tolle, Kristin M" uniqKey="Tolle K" first="Kristin M." last="Tolle">Kristin M. Tolle</name>
</noRegion>
<name sortKey="Chen, Hsinchun" sort="Chen, Hsinchun" uniqKey="Chen H" first="Hsinchun" last="Chen">Hsinchun Chen</name>
<name sortKey="Tolle, Kristin M" sort="Tolle, Kristin M" uniqKey="Tolle K" first="Kristin M." last="Tolle">Kristin M. Tolle</name>
<name sortKey="Tolle, Kristin M" sort="Tolle, Kristin M" uniqKey="Tolle K" first="Kristin M." last="Tolle">Kristin M. Tolle</name>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Informatique/explor/SgmlV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001B81 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001B81 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Informatique
   |area=    SgmlV1
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     ISTEX:F89A78E6F114B4601DE09E6221D5DF8DC95B240F
   |texte=   Comparing noun phrasing techniques for use with medical digital library tools
}}

Wicri

This area was generated with Dilib version V0.6.33.
Data generation: Mon Jul 1 14:26:08 2019. Site generation: Wed Apr 28 21:40:44 2021