Chatbots: Autoexpansion Approach to Improve Natural Language Automatic Dialogs

Abstract

Chatbots belong to a large family of software robots that aim to gracefully integrate human spoken interactions as interface. Most of the proposals in the field intend to solve severe limitations of the automatic processing of natural language. This paper is part of a project called PTAH, that implements a prototype able to ask and answer about a topic in Spanish. Although previous work solved much of the training and language-based strategies, there is still poor resources to make the bot understand alternatives to answer specific questions or problems. This paper presents an approach called auto-expansion with an original combination of Morphosyntactic-Linguistic-Wavelets and certain Machine Learning techniques. As part of the scope, the basic preliminary theory is introduced, along with detailed description of the self-expansion proposal and some of the prototype's state of implementation, tests and statistical analysis. Authors intend to show the goodness of the proposal.