Talk: "A Deep Reinforcement Learning Chatbot" by Iulian Serban

NB: Date change! This meetup has been moved from the 12th to 19th of September.

Abstract

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including sequence-to-sequence and latent variable neural network models. By applying reinforcement learning to crowd-sourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed excellent.

Speaker Bio

Iulian Serban is a PhD candidate at MILA, where he investigates deep learning and reinforcement learning methods for dialogue and other natural language processing applications. Iulian is supervised by Yoshua Bengio, Aaron Courville and Joelle Pineau. He holds an MSc in machine learning from University College London, and a BSc in theoretical mathematics and statistics from Copenhagen University. Previously, Iulian worked at DigiCorpus ApS, where he developed a physiotherapy computer vision system, now deployed in clinics across Denmark.