DeveloperWeek 2020

Virtual assistants have become an omnipresent force, extending into our personal and professional endeavors, and the number of voice assistants is forecast to jump threefold to eight billion by 2023. But while technology has made major inroads in enabling assistants to answer simple questions or commands with one-to-one responses (such as, “what time is it?” or “set a timer for 2 minutes”), most of us can recall a frustrating experience when a chatbot or smart speaker didn’t reply with a relevant answer. In fact, according to a recent study, Amazon's Alexa, Apple's Siri, Google Assistant and Microsoft's Cortana are less capable of answering questions correctly than they were two years ago.

So, how can we enable virtual assistants to understand us better? Can we design more robust interactions that cater to the nuances of human communication? In this session, Carolina Belmonte, a TEKsystems’ practice architect of data analytics and insights, will explore natural language intent recognition and how developers can build a framework to improve human-robot interaction.

Leveraging real-world experience from leading AI implementations for conversational platforms, virtual agents and chatbots across TEKsystems’ customer base of 80% of the Fortune 500, Carolina will provide insight into natural language processing (NLP), intent recognition and “many-to-one” network mappings. Attendees will leave with tactical knowledge of the fundamentals for developing a robust framework that will enable virtual assistants to understand and appropriately respond to a significant variety of user inputs.