Distributed Vector Representations of Words in the Sigma Cognitive Architecture

摘要: Recently reported results with distributed-vector word representations in natural language processing make them appealing for incorporation into a general cognitive architecture like Sigma. This paper describes new algorithm learning such from large, shallow information resources, and how this can be implemented via small modifications to The effectiveness speed of the are evaluated comparison an external simulation it state-of-the-art algorithms. more limited experiments Sigma also promising, but work is required reach simulation.