Title | ||
---|---|---|
Why discourse structures in medical reports matter for the validity of automatically generated text knowledge bases. |
Abstract | ||
---|---|---|
The automatic analysis of medical full-texts currently suffers from neglecting text coherence phenomena such as reference relations between discourse units. This has unwarranted effects on the description adequacy of medical knowledge bases automatically generated from texts. The resulting representation bias can be characterized in terms of artificially fragmented, incomplete and invalid knowledge structures. We discuss three types of textual phenomena (pronominal and nominal anaphora, as well as textual ellipsis) and outline basic methodologies how to deal with them. |
Year | Venue | Keywords |
---|---|---|
1998 | Studies in Health Technology and Informatics | natural language processing,pathology |
Field | DocType | Volume |
Information retrieval,Computer science,Artificial intelligence,Natural language processing | Conference | 52 |
ISSN | Citations | PageRank |
0926-9630 | 2 | 0.52 |
References | Authors | |
6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Udo Hahn | 1 | 937 | 88.14 |
Martin Romacker | 2 | 450 | 48.44 |
Stefan Schulz | 3 | 29 | 5.15 |