Research in Natural Language Understanding
Abstract
This report is the second quarterly progress report of the ARPA- sponsored Natural Language Understanding project at BBN. The goals of the project are to develop techniques required for fluent and effective communication between a decision maker and an intelligent computerized display system in the context of complex decision tasks such as military command and control. This problem is approached as a natural language understanding problem, since most of the techniques required would still be necessary for an artificial language designed specifically for the task. This report discusses three questions involved in representing and using natural conceptual information: (1) What kind of thing is a concept, (2) How can semantic interpretation information be represented appropriately in an associative network memory model, and (3) What kinds of marker-passing algorithms can be used to perform incremental semantic interpretation concurrently with parsing in a distributed activation memory network containing large numbers of interpretation rules.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1978
- Accession Number
- ADA053958
Entities
People
- William A. Woods
Organizations
- BBN Technologies