A Comparison and Critique of Natural Language Understanding Tools

摘要

In the last 10 years, various cloud platforms enabled developers to easily create applications able to understand, with some limitations, natural languages. Nowadays, such cloud plat-forms for natural language understanding (NLU) are widely used, thanks to the rise of multiple chat services and conversational assistants on our mobile devices. This paper compares and analyses the main cloud-based NLU platforms, both from a descriptive and from a performance-based point of view. For the descriptive analysis, a taxonomy is proposed and six cloud platforms are analyzed. The performance evaluation, instead, compares three of these platforms, highlighting strengths and weaknesses of the different NLU tools.