Chatbot-based assertion generation from natural language specifications

Abstract

We present an approach to simplify the task of extracting assertions from specifications given in natural language. Our goal is to accept and understand a broad range of linguistic variation, allowing the author of the natural language specifications to express herself freely. To enable this, we leverage the Dialogflow framework from Google. Dialogflow is usually used to build chatbots that understand and respond to conversational statements. We have trained a Dialogflow model to recognize a range of different natural language expressions of properties, and to identify key information inside the expression. The model responses to each statement with a generated SystemVerilog assertion whose semantic meaning is equivalent to that of the English statement.