Speaker "Manisha Srivastava" Details Back



Current State of Chatbots


Chatbots have come a long way from ELIZA, the first chatbot developed 50 years ago at MIT, to today's Siri, Alexa, and Cortana. Recent advances in machine learning and natural language processing are bringing realistic conversations with bots ever closer to reality. Given the best-case scenario, you could speak naturally to an intelligent agent, and it would do the job - order a taxi, shop for groceries, update on weather, make a reservation etc. But the reality is far from this; the current chatbots still have a hard time keeping a conversation going - they don't fully understand the user's need and forget the context of the conversation, leading to robotic and impersonal experience. In this talk, we’ll look at the current state of chatbot technologies and their limitations, before wrapping up with examples from Amazon customer service.


Manisha Srivastava is a machine learning scientist at Amazon Customer Service, working to improve the customer experience using NLP techniques. Prior to Amazon she worked at TripAdvisor, focusing on using machine learning to improve the quality of business listings. She received her masters degree in Computer Engineering from Texas A&M University, College Station. Before this she worked as data scientist at General Electric Research lab India, applying predictive analytics in domains like healthcare, oil & gas, and wind energy. She did her undergraduate studies at Indian Institute of Technology, Guwahati.