Proposal Towards a Personalized Knowledge-powered Self-play Based Ensemble Dialog System

Abstract

This is the application document for the 2019 Amazon Alexa competition. We give an overall vision of our conversational experience, as well as a sample conversation that we would like our dialog system to achieve by the end of the competition. We believe personalization, knowledge, and self-play are important components towards better chatbots. These are further highlighted by our detailed system architecture proposal and novelty section. Finally, we describe how we would ensure an engaging experience, how this research would impact the field, and related work.

14 pages. Originally written for the 2019 Amazon Alexa application

References in corpus (16)

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• Topic Aware Neural Response Generation
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• Exploration by Random Network Distillation
• A Deep Reinforcement Learning Chatbot
• Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
• DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
• Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
• Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
• Deep Learning Based Chatbot Models
• Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
• OK Google, What Is Your Ontology? Or: Exploring Freebase Classification to Understand Google's Knowledge Graph
• RubyStar: A Non-Task-Oriented Mixture Model Dialog System
• Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
• Why Do Neural Response Generation Models Prefer Universal Replies?