Implicational Molecules: A Method for Extracting Meaning from Input Sentences
Proceedings of the First International Joint Conference on Artificial Intelligence. Psychological Modeling. Pages 641-648.
Abstract
A generally overlooked possibility for extracting pragmatic meaning from sentence inputs is discussed, This possibility draws upon the psychology of the subjective attribution of causes to stimulus events. Application to the design of conversational programs is feasible, although the present work concerns application to the simulation of a belief system, Simple sentences known by the system are grouped into categorical types, An "implicational molecule" is a meaningful set of sentence types with linked elements, for example: A does X, X causes Y1 . A wants Y, One important way in which meaning can be ascribed to an input sentence is to use it as the basis for a molecule which is then "filled" by other information in the system, This notion is defined ~thematically, and a programming algorithm outlined, The possibility of recursive use of a molecule-filling routine gives the process heuristic overtones.
@inproceedings{ijcai1969p56,
title = {Implicational Molecules: A Method for Extracting Meaning from Input Sentences},
author = {Abelson, Robert P. and Reich, Carol M.},
booktitle = {Proceedings of the First International Joint Conference on
Artificial Intelligence, {IJCAI-69}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Donald E. Walker and David C. Cooper},
pages = {641--648},
year = {1969},
month = {5},
note = {Psychological Modeling},
url = {https://ijcai.org/proceedings/1969/56},
}
TY - CPAPER TI - Implicational Molecules: A Method for Extracting Meaning from Input Sentences AU - Abelson, Robert P. AU - Reich, Carol M. T2 - Proceedings of the First International Joint Conference on Artificial Intelligence, IJCAI-69 PB - International Joint Conferences on Artificial Intelligence PY - 1969 SP - 641 EP - 648 UR - https://ijcai.org/proceedings/1969/56 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
