Communications of the ACM - Special issue on parallelism
In-Depth Understanding: A Computer Model of Integrated Processing for Narrative Comprehension
In-Depth Understanding: A Computer Model of Integrated Processing for Narrative Comprehension
Dynamic Memory: A Theory of Reminding and Learning in Computers and People
Dynamic Memory: A Theory of Reminding and Learning in Computers and People
Understanding Natural Language
Understanding Natural Language
Pattern-Directed Inference Systems
Pattern-Directed Inference Systems
The ROBOT System: Natural language processing applied to data base query
ACM '78 Proceedings of the 1978 annual conference
Semantic interpretation against ambiguity
Semantic interpretation against ambiguity
Unifying representation and generalization: understanding hierarchically structured objects
Unifying representation and generalization: understanding hierarchically structured objects
Computational Linguistics
Computational Linguistics
Description strategies for naive and expert users
ACL '85 Proceedings of the 23rd annual meeting on Association for Computational Linguistics
Knowledge-based understanding on a small machine
SIGSMALL '90 Proceedings of the 1990 ACM SIGSMALL/PC symposium on Small systems
Automated knowledge acquisition from regulatory texts
IEEE Expert: Intelligent Systems and Their Applications
Using lexical and relational similarity to classify semantic relations
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Hi-index | 48.22 |
The performance of a natural language processing system should improve as it reads more and more texts. This is true both for systems intended as cognitive models and for practical text processing systems. Permanent long-term memory should be useful during all stages of text understanding. For example, if, while reading a patent abstract about a new disk drive, a system can retrieve information about similar objects from memory, processing should be simplified. However, most natural language programs do not exhibit such learning behavior. We describe in this article how RESEARCHER, a program that reads, remembers and generalizes from patent abstracts, makes use of its automatically generated memory to assist in low-level text processing, primarily involving disambiguation that could be accomplished no other way. We describe both RESEARCHER's basic understanding methods and the integration of memory access. Included is an extended example of RESEARCHER processing a patent abstract by using information about several other abstracts already in memory.