Incorporating Semantics Within a Connectionist Model and a Vector Processing Model.
Richard Boyd, James R. Driscoll, Inien Syu · Text REtrieval Conference · 1993
Semantic information obtained from the public domain 1911 version of Roget's thesaurus is combined with keywords to measure similarity between natural language topics and documents. Two approaches are explored. In one appraoch, a combination of keyword and semantic relevance is achieved by using the vector processing model for calculating similarity, but extanding the use of keyword weight by using individual weights for each of its meanings. This approach is based on the database concept of semantic modeling and the linguistic concept of thematic role. Iy is applicable to both routing and archival retreival. The second approach is especailly suited for routing. It is based on an AI connncectionist model. In this approach, a probabilistic inference network is modified using semantic information to achieve a competitive activation mechanism taht can be used for calculating similarity