Deep Learning for Conversational Intelligence on Analytics Data
By 2020, 50% of analytic queries will be generated using search, natural-language processing or voice. A new generation of conversation-first business intelligence assistants are emerging, helping employees to access their company decision-making data in natural language. In this talk, we will present the technologies and architectures that can be leveraged to build such systems, and their challenges in term of supervision, transparency and domain generalization.
Christophe Bourguignat is a senior Data Scientist, Kaggle Master, and blogger. He joined the AXA Data Innovation Lab, and then co-founded Zelros, a parisian startup developing a virtual assistants platform for employees, used by large firms like Total, Air Liquide, AXA. Christophe also founded FrenchData, an influent think tank promoting the french data scene.