Steps toward deep lexical acquisition

Authors:
Sourabh Niyogi
Affiliations:
Massachusetts Institute of Technology
Venue:
PMHLA '05 Proceedings of the Workshop on Psychocomputational Models of Human Language Acquisition
Year:
2005

Citing 5
Cited 0

Qualitative process theory

Artificial Intelligence - Special volume on qualitative reasoning about physical systems
Commonsense metaphysics and lexical semantics

Computational Linguistics - Special issue of the lexicon
The structure-mapping engine: algorithm and examples

Artificial Intelligence
Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project

Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project
Adding predicate argument structure to the Penn TreeBank

HLT '02 Proceedings of the second international conference on Human Language Technology Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

I describe steps toward "deep lexical acquisition" based on naive theories, motivated by modern results of developmental psychology. I argue that today's machine learning paradigm is inappropriate to take these steps. Instead we must develop computational accounts of naive theory representations, mechanisms of theory acquisition, and the mapping of naive theories to lexicalizable concepts. This will enable our theories to describe the flexibility of the human conceptual apparatus.