Software engineering collaboration is hard. Software engineers spend more than 70% of their time learning about their own team’s source code. Enormous size, constant change and intricate dependencies of the source code are the main factors at play. While one software engineer is not responsible for all lines of code for their company, a single line of their code can break the entire company’s app.
To help software engineers, we translate source code into natural language to make it easier to search, navigate and understand. At Quod AI, we are building an AI knowledge assistant which generate documentation (in Q&A format) from raw source code. In order to do that, we use neural network models, natural language processing algorithms and statistical models. We retrieve, store and analyze the source code and its history to get insights from the evolution of the code.
In this talk we will share some of the insights that we gained from analyzing more than 300 millions lines of code.
Misha Filippov is chief scientist at Quod AI and a research fellow at University College London. At Quod AI he is applying natural language processing, deep learning and statistical models to explain source code in plain English.
Misha holds a PhD in physics from Nanyang Technological University. As a mathematical physicist he studied the dynamics of complex systems and has built mathematical and AI models for tsunami prediction, tropical atmosphere, the housing market, historical information and visual cortex of the human brain. His models have been used by NASA & the Monetary Authority of Singapore.