Language Acquisition in Computers (1206.0042v1)

Abstract: This project explores the nature of language acquisition in computers, guided by techniques similar to those used in children. While existing natural language processing methods are limited in scope and understanding, our system aims to gain an understanding of language from first principles and hence minimal initial input. The first portion of our system was implemented in Java and is focused on understanding the morphology of language using bigrams. We use frequency distributions and differences between them to define and distinguish languages. English and French texts were analyzed to determine a difference threshold of 55 before the texts are considered to be in different languages, and this threshold was verified using Spanish texts. The second portion of our system focuses on gaining an understanding of the syntax of a language using a recursive method. The program uses one of two possible methods to analyze given sentences based on either sentence patterns or surrounding words. Both methods have been implemented in C++. The program is able to understand the structure of simple sentences and learn new words. In addition, we have provided some suggestions regarding future work and potential extensions of the existing program.