Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions

Abstract

We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been built so far, and the gaping holes we have not filled yet. We present a biased view, focusing on work done by our own group, while citing related work in each area. In particular, we discuss in detail the properties of continual learning, providing engaging content, and being well-behaved -- and how to measure success in providing them. We end with a discussion of our experience and learnings, and our recommendations to the community.

References in corpus (24)

• Sequence to Sequence Learning with Neural Networks
• Overcoming catastrophic forgetting in neural networks
• Federated Learning: Strategies for Improving Communication Efficiency
• A Neural Conversational Model
• VQA: Visual Question Answering
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• Towards a Human-like Open-Domain Chatbot
• Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
• A Deep Reinforcement Learning Chatbot
• Conversational AI: The Science Behind the Alexa Prize
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• Building a Conversational Agent Overnight with Dialogue Self-Play
• Tracking the World State with Recurrent Entity Networks
• Rasa: Open Source Language Understanding and Dialogue Management
• DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
• ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons
• Learning through Dialogue Interactions by Asking Questions
• Dialogue Learning With Human-In-The-Loop
• Learning Robust Dialog Policies in Noisy Environments
• Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
• Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles
• Why Build an Assistant in Minecraft?
• I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents
• All-in-One Image-Grounded Conversational Agents

Cited by in corpus (9)

• Survey of Hallucination in Natural Language Generation
• SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
• Controlling Style in Generated Dialogue
• Robust Conversational AI with Grounded Text Generation
• Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation
• Enhancing Task-Oriented Dialogues with Chitchat: a Comparative Study Based on Lexical Diversity and Divergence
• Local Knowledge Powered Conversational Agents
• Investigating Robustness of Dialog Models to Popular Figurative Language Constructs
• An Approach to Inference-Driven Dialogue Management within a Social Chatbot