Natural Language Processing of Captions for Retrieving Multimedia Data.

摘要

This report describes the current implementation status of an intelligent information retrieval system, MARIE, that employs natural language processing techniques. Descriptive captions are used to identify photographic images concerning various military projects. The captions are written in a restricted form of English and consist mostly of descriptive noun phrases and nominal compounds. The captions are parsed to produce a logical form from which nouns and verbs are extracted to form the primary keywords. The keywords and the logical form together index the multimedia object User queries are also specified in natural language. A two-phase search process is used to find the caption(s) that best match the query. A coarse-grain match process uses the 7 the logical form during semantic analysis, generating the keywords for use by the coarse-grain match process, setting inner case values and correlations between models, and performing the fine-grain matching.