Abstract
The Teachable Language Comprehender (TLC) is a program designed to be capable of being taught to “comprehend” English text. When text which the program has not seen before is input to it, it comprehends that text by correctly relating each (explicit or implicit) assertion of the new text to a large memory. This memory is a “semantic network” representing factual assertions about the world.
The program also creates copies of the parts of its memory which have been found to relate to the new text, adapting and combining these copies to represent the meaning of the new text. By this means, the meaning of all text the program successfully comprehends is encoded into the same format as that of the memory. In this form it can be added into the memory.
Both factual assertions for the memory and the capabilities for correctly relating text to the memory's prior content are to be taught to the program as they are needed. TLC presently contains a relatively small number of examples of such assertions and capabilities, but within the system, notations for expressing either of these are provided. Thus the program now corresponds to a general process for comprehending language, and it provides a methodology for adding the additional information this process requires to actually comprehend text of any particular kind.
The memory structure and comprehension process of TLC allow new factual assertions and capabilities for relating text to such stored assertions to generalize automatically. That is, once such an assertion or capability is put into the system, it becomes available to help comprehend a great many other sentences in the future. Thus the addition of a single factual assertion or linguistic capability will often provide a large increment in TLC's effective knowledge of the world and in its overall ability to comprehend text.
The program's strategy is presented as a general theory of
- ABELSON, R. P., A.ND CARROLL, J. D. Computer simulation of individual belief systems. Amer. Behav. Sci. 8, 9 (1965), 24-30.Google ScholarCross Ref
- BOBROW, D. G., MURPhy, D. L., AND TEITELMAN, W. The BBN LISP system. Bolt Beranek and Newman Inc., Cambridge, Mass., 1968.Google Scholar
- CHOMSKY, N. Aspecls of the Theory of Syntax. MIT Press, Cambridge, Mass., 1965.Google Scholar
- COLLINS, A. M., AND QUILLIAN, M. R. Retrieval time from semantic memory. Rep. No. 1692. Bolt Beranek and Newman Inc., Cambridge, Mass., 1968. To appear in J. Verb. Learn. Verb. Behav. (1969).Google Scholar
- FEIGENBAUM, E. A., AND FELDMAN, J. Computers and Thought. McGraw-Hill, New York, 1963. Google ScholarDigital Library
- KUNO, S. The predictive analyzer and a path elimination technique. Comm. ACM 8, 7 (July, 1965), 453-462. Google ScholarDigital Library
- LONGYEAR, C. The semantic rule. Rep. No. 67TMP-55, General Electric TEMPO Project, Santa Barbara, Calif., 1967.Google Scholar
- MINSKY, M. Semantic Information Processing. MIT Press, Cambridge, Mass., 1968. Google ScholarDigital Library
- NEWELL, A., SHAW, J. C., AND SIMON, H. A. The processes of creative thinking. In Contemporary Approaches to Creative Thinking, H. E. Gruber, G. Terrell, and M. Wertheimer (Eds.), Atherton Press, New York, 1962, pp. 63-119.Google Scholar
- PIAGET, J. The Psyehology of Intelligence. Routledge and Kegan Paul, London, 1950.Google Scholar
- QUILLIAN, M. R. Semantic Memory. In Semantic Information Processing, M. Minsky, The MIT Press, Cambridge, Mass., 1968.Google Scholar
- Word concepts: a theory and simulation of some basic semantic capabilities. Behav. Sci. 12 (1967), 410-430.Google ScholarCross Ref
- ----, WORTMAN, P. AND BAYLOR, G. W. The programable Piaget: Behavior from the standpoint of a radical computerist. Unpublished dittoed paper, Carnegie-Melon U., Pittsburgh, Pa., 1965.Google Scholar
- RAPHAEL, B., BOBROW, D. G., FEIN, L., AND YOUNG, Z. W. A Brief Survey of Computer Languages for Symbolic and Algebraic Manipulation. North-Holland Pub. Co., Amsterdam, 1968.Google Scholar
- REITMAN, W. R. Cognition and Thought: An Information Processing Approach. Wiley, New York, 1965.Google Scholar
- SIKLOSSY, L., AND SIMON, H. A. Some semantic methods for language processing. Complex information processing Paper 129, Carnegie-Mellon U., Pittsburgh, Penn., 1968.Google Scholar
- SIMMONS, R. F. Answering English questions by computer: a survey. Comm. ACM 8, 1 (Jan. 1965), 53-70. Google ScholarDigital Library
- -- AND BURGER, J. F. A semantic analyzer for English sentences. Rep. No. SP 2987, Syst. Develop. Corp., Santa Monica, Calif., 1968.Google Scholar
- TESLER, L., ENEA, H., AND COLBY, K. M. A directed graph representation for computer simulation of belief systems. Dep. Comput. Sci., Stanford U., Stanford, Calif., 1967.Google Scholar
- THOMPSON, F. B. The deacon project. Rep. No. 65TMP-69, General Electric TEMPO Project, Santa Barbara, Calif., 1965.Google Scholar
- THORNE, J. P., BRATLEY, P., AND DEWAR, H. The syntactic analysis of English by machine. In Machine Intelligence 3, Donald Michie (Ed.), American Elsevier, New York, 1968, pp. 281-309.Google Scholar
- WEIZENBAUM, J. Contextual understanding by computer. Comm. ACM 10, 8 (Aug. 1967), 474-480. Google ScholarDigital Library
Index Terms
- The teachable language comprehender: a simulation program and theory of language
Recommendations
Exploring language technologies to provide support to WCAG 2.0 and E2R guidelines
Interacción '15: Proceedings of the XVI International Conference on Human Computer InteractionPart of citizenship faces accessibility barriers when they read and understand texts containing long sentences, unusual words, complex linguistic structures, etc. Readability and understanding should be considered when texts are created. In order to ...
Cognitive architecture for natural language comprehension
Human interactions with computers in natural language have always been a challenging task. Numerous computational systems are being designed to bring this interaction as close to the natural language commands as possible. Cognitive architectures are ...
A method for the computation of the semantic similarity and relatedness between natural language words
This paper develops methods for calculating the semantic similarity (closeness)-relatedness of natural language words. The concept of semantic relatedness allows one to construct algorithmic models for the context-linguistic analysis with a view to ...
Comments