The RLLChatbot: a solution to the ConvAI challenge
This work addresses the challenge of maintaining coherent open-ended conversations for conversational AI systems, though it is incremental as it builds on existing deep learning and reinforcement learning tools.
The authors tackled the problem of building a robust open-domain conversational agent by developing the RLLChatbot for the 2017 ConvAI challenge, resulting in significant improvements in Recall@k scores through novel ranking and selection methods and a new open-source dataset.
Current conversational systems can follow simple commands and answer basic questions, but they have difficulty maintaining coherent and open-ended conversations about specific topics. Competitions like the Conversational Intelligence (ConvAI) challenge are being organized to push the research development towards that goal. This article presents in detail the RLLChatbot that participated in the 2017 ConvAI challenge. The goal of this research is to better understand how current deep learning and reinforcement learning tools can be used to build a robust yet flexible open domain conversational agent. We provide a thorough description of how a dialog system can be built and trained from mostly public-domain datasets using an ensemble model. The first contribution of this work is a detailed description and analysis of different text generation models in addition to novel message ranking and selection methods. Moreover, a new open-source conversational dataset is presented. Training on this data significantly improves the Recall@k score of the ranking and selection mechanisms compared to our baseline model responsible for selecting the message returned at each interaction.