Comprehension grammars generated from machine learning of natural languages

作者:Patrick Suppes, Michael Böttner, Lin Liang

摘要

We are developing a theory of probabilistic language learning in the context of robotic instruction in elementary assembly actions. We describe the process of machine learning in terms of the various events that happen on a given trial, including the crucial association of words with internal representations of their meaning. Of central importance in learning is the generalization from utterances to grammatical forms. Our system derives a comprehension grammar for a superset of a natural language from pairs of verbal stimuli likeGo to the screw! and corresponding internal representations of coerced actions. For the derivation of a grammar no knowledge of the language to be learned is assumed but only knowledge of an internal language.

论文关键词:learning, natural language, grammatical generalization, robotics

论文评审过程:

论文官网地址:https://doi.org/10.1007/BF01007462