Advertisement

ParseTalk — The System Context

Chapter
  • 195 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1744)

Abstract

Though the principles I propose for the analyses of degree expressions can be employed within a broad variety of natural language processing environments — and I mentioned some others before (Appelt et al., 1993; Neumann et al., 1997; Staab et al., 1999) — the issue of howthese principles are put to work in a particular setting is interesting in itself.

On the one hand, the setting is given by the range of texts to which the text knowledge extraction task is applied. Two types of texts have been in the research focus, viz. expository texts about product reviews from the information technology domain and histology reports from a medical diagnosis domain (Hahn et al., 1999). Either of the two text domains is very appropriate for testing the adequacy of the degree expression understanding methods, because in both types of text grading information plays an extremely important role. Properties of products as well as diagnosed irregularities are very often described in graded terms (cf. (2.1)).

Keywords

Noun Phrase Description Logic Central Processing Unit Hard Disk Drive Conceptual System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Personalised recommendations