Semantic Extensions To Text Retrieval

Current information retrieval systems focus on the use of keywords to respond to user queries. We propose using surface level knowledge to improve retrieval accuracy. Our approach is based on (1) the database concept of semantic modeling (particularly entity attributes and relationship properties) and (2) the linguistic concept of thematic roles, also referred to in the literature as participant roles, semantic roles, and case roles. We include an example to illustrate our approach. Some test results are also reported