Using Memory in Text Understanding

Lebowitz, Michael

Text processing undoubtedly takes place at many levels simultaneously. In this paper, we discuss how the access of detailed long-term memory can be used in low-level text processing in the context of a computer system, RESEARCHER, that reads, generalizes, and remembers information form patent abstracts. We show specific points where memory can be applied during text processing, rather than just suggesting general principles. In particular, we focus on how linguistically ambiguous structures can be resolved using memory (and only using memory). A computer example of RESEARCHER applying our memory application principles (with a simulated detailed memory) is presented.



More About This Work

Academic Units
Computer Science
Department of Computer Science, Columbia University
Columbia University Computer Science Technical Reports, CUCS-121-84
Published Here
February 17, 2012