Summarization of an online medical encyclopedia

Marcelo Fiszman; Thomas C. Rindflesch; Halil Kilicoglu

doi:10.3233/978-1-60750-949-3-506

Summarization of an online medical encyclopedia

Marcelo Fiszman, Thomas C. Rindflesch, Halil Kilicoglu

Research output: Contribution to journal › Article › peer-review

Abstract

We explore a knowledge-rich (abstraction) approach to summarization and apply it to multiple documents from an online medical encyclopedia. A semantic processor functions as the source interpreter and produces a list of predications. A transformation stage then generalizes and condenses this list, ultimately generating a conceptual condensate for a given disorder topic. We provide a preliminary evaluation of the quality of the condensates produced for a sample of four disorders. The overall precision of the disorder conceptual condensates was 87%, and the compression ratio from the base list of predications to the final condensate was 98%. The conceptual condensate could be used as input to a text generator to produce a natural language summary for a given disorder topic.

Original language	English (US)
Pages (from-to)	506-510
Number of pages	5
Journal	Studies in health technology and informatics
Volume	107
DOIs	https://doi.org/10.3233/978-1-60750-949-3-506
State	Published - Jan 1 2004
Externally published	Yes

Keywords

Automatic Summarization
Knowledge Representation
Natural Language Processing

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Health Information Management

Access to Document

10.3233/978-1-60750-949-3-506

Cite this

@article{11ce82ee4c524d95b57021c4b7d27aa5,

title = "Summarization of an online medical encyclopedia",

abstract = "We explore a knowledge-rich (abstraction) approach to summarization and apply it to multiple documents from an online medical encyclopedia. A semantic processor functions as the source interpreter and produces a list of predications. A transformation stage then generalizes and condenses this list, ultimately generating a conceptual condensate for a given disorder topic. We provide a preliminary evaluation of the quality of the condensates produced for a sample of four disorders. The overall precision of the disorder conceptual condensates was 87%, and the compression ratio from the base list of predications to the final condensate was 98%. The conceptual condensate could be used as input to a text generator to produce a natural language summary for a given disorder topic.",

keywords = "Automatic Summarization, Knowledge Representation, Natural Language Processing",

author = "Marcelo Fiszman and Rindflesch, {Thomas C.} and Halil Kilicoglu",

year = "2004",

month = jan,

day = "1",

doi = "10.3233/978-1-60750-949-3-506",

language = "English (US)",

volume = "107",

pages = "506--510",

journal = "Studies in Health Technology and Informatics",

issn = "0926-9630",

publisher = "IOS Press",

}

TY - JOUR

T1 - Summarization of an online medical encyclopedia

AU - Fiszman, Marcelo

AU - Rindflesch, Thomas C.

AU - Kilicoglu, Halil

PY - 2004/1/1

Y1 - 2004/1/1

N2 - We explore a knowledge-rich (abstraction) approach to summarization and apply it to multiple documents from an online medical encyclopedia. A semantic processor functions as the source interpreter and produces a list of predications. A transformation stage then generalizes and condenses this list, ultimately generating a conceptual condensate for a given disorder topic. We provide a preliminary evaluation of the quality of the condensates produced for a sample of four disorders. The overall precision of the disorder conceptual condensates was 87%, and the compression ratio from the base list of predications to the final condensate was 98%. The conceptual condensate could be used as input to a text generator to produce a natural language summary for a given disorder topic.

AB - We explore a knowledge-rich (abstraction) approach to summarization and apply it to multiple documents from an online medical encyclopedia. A semantic processor functions as the source interpreter and produces a list of predications. A transformation stage then generalizes and condenses this list, ultimately generating a conceptual condensate for a given disorder topic. We provide a preliminary evaluation of the quality of the condensates produced for a sample of four disorders. The overall precision of the disorder conceptual condensates was 87%, and the compression ratio from the base list of predications to the final condensate was 98%. The conceptual condensate could be used as input to a text generator to produce a natural language summary for a given disorder topic.

KW - Automatic Summarization

KW - Knowledge Representation

KW - Natural Language Processing

UR - http://www.scopus.com/inward/record.url?scp=70349454395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349454395&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-949-3-506

DO - 10.3233/978-1-60750-949-3-506

M3 - Article

C2 - 15360864

AN - SCOPUS:70349454395

VL - 107

SP - 506

EP - 510

JO - Studies in Health Technology and Informatics

JF - Studies in Health Technology and Informatics

SN - 0926-9630

ER -

Summarization of an online medical encyclopedia

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other links

Fingerprint

Cite this