Recent Advances in HNC's Context Vector Information Retrieval Technology

Over the past few years, HNC has developed a neural network based, vector space approach to text retrieval. This approach, embodied in a system called MatchPlus, allows the user to retrieve information on the basis of meaning and context of a free text query. The MatchPlus system uses a neural network based constrained selorganization technique to learn word stem interrelationships directly 3om a training corpus, thereby eliminating the need for hand crafted linguistic knowledge bases and their often substantial maintenance requirements. This paper presents results from recent enhancements to the basic MatchPlus concept. These enhancements include the development of a one step learning law that greatly reduces the amount of time andor computational resources required to train the system, and the development of a prototype multilingual (English and Spanish) text retrieval system. TIPSTER TEXT PROGRAM PHASE II: Proceedings of a Workshop held at Vienna, Virginia, May 6-8, 1996. Sponsored by the Defense Advanced Research Projects Agency.