Document Detail


Discourse structures in medical reports--watch out! The generation of referentially coherent and valid text knowledge bases in the MEDSYNDIKATE system.
MedLine Citation:
PMID:  10075128     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
The automatic analysis of medical narratives currently suffers from neglecting text structure phenomena such as referential relations between discourse units. This has unwarranted effects on the descriptional adequacy of medical knowledge bases automatically generated from texts. The resulting representation bias can be characterized in terms of incomplete, artificially fragmented and referentially invalid knowledge structures. We focus here on four basic types of textual reference relations, viz. pronominal and nominal anaphora, textual ellipsis and metonymy and show how to deal with them in an adequate text parsing device. Since the types of reference relations we discuss show an increasing dependence on conceptual background knowledge, we stress the need for formally grounded, expressive conceptual representation systems for medical knowledge. Our suggestions are based on experience with MEDSYNDIKATE, a medical text knowledge acquisition system designed to properly deal with various sorts of discourse structure phenomena.
Authors:
U Hahn; M Romacker; S Schulz
Related Documents :
7231228 - Modular design of microcomputer-based medical instruments.
12743648 - Informatics united: exemplary studies combining medical informatics, neuroinformatics a...
16849918 - Improving the human readability of arden syntax medical logic modules using a concept-o...
22653088 - The meanings associated with medicines in heart failure patients.
17976128 - Identification of medication non-adherence factors in adolescent transplant patients: t...
9700568 - Critical assessment of the involvement of perforations, spinules, and spine branching i...
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  International journal of medical informatics     Volume:  53     ISSN:  1386-5056     ISO Abbreviation:  Int J Med Inform     Publication Date:  1999 Jan 
Date Detail:
Created Date:  1999-05-10     Completed Date:  1999-05-10     Revised Date:  2007-11-15    
Medline Journal Info:
Nlm Unique ID:  9711057     Medline TA:  Int J Med Inform     Country:  IRELAND    
Other Details:
Languages:  eng     Pagination:  1-28     Citation Subset:  IM    
Affiliation:
Freiburg University, Computational Linguistics Lab, Germany. hahn@coling.uni-freiburg.de
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Artificial Intelligence*
Humans
Information Storage and Retrieval
Information Systems*
Information Theory
Linguistics
Natural Language Processing*
Software
Terminology as Topic

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Antistressor effect of Withania somnifera.
Next Document:  Development of a cross-thesaurus with Internet-based refinement supported by UMLS.