Evolutionary Sentence Building for Chatterbots
Chatterbots are computer programs that simulate intelligent conversation. They make use of various techniques such as pattern matching, indexing, sentence reconstruction, and even natural language processing. In this paper we present an approach to chatterbots that mixes pattern matching with indexing and query matching methods inspired from information retrieval. We propose a model in which new sentences can be produced from existing ones using an evolutionary algorithm adapted to the structure of the natural language.