Robust Conversational AI with Grounded Text Generation
arXiv:2009.03457
Abstract
This article presents a hybrid approach based on a Grounded Text Generation (GTG) model to building robust task bots at scale. GTG is a hybrid model which uses a large-scale Transformer neural network as its backbone, combined with symbol-manipulation modules for knowledge base inference and prior knowledge encoding, to generate responses grounded in dialog belief state and real-world knowledge for task completion. GTG is pre-trained on large amounts of raw text and human conversational data, and can be fine-tuned to complete a wide range of tasks. The hybrid approach and its variants are being developed simultaneously by multiple research teams. The primary results reported on task-oriented dialog benchmarks are very promising, demonstrating the big potential of this approach. This article provides an overview of this progress and discusses related methods and technologies that can be incorporated for building robust conversational AI systems.
References in corpus (22)
- Overcoming catastrophic forgetting in neural networks
- Language Models are Few-Shot Learners
- A Neural Conversational Model
- Deep Learning: A Critical Appraisal
- The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
- Towards a Human-like Open-Domain Chatbot
- A Simple Language Model for Task-Oriented Dialogue
- Why We Need New Evaluation Metrics for NLG
- Rasa: Open Source Language Understanding and Dialogue Management
- DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
- SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
- BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
- Generative Deep Neural Networks for Dialogue: A Short Review
- Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
- Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning
- Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context
- Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
- Learning to Compose Skills
- ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
- Are distributional representations ready for the real world? Evaluating word vectors for grounded perceptual meaning
- Conversation Learner -- A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems
- Template Guided Text Generation for Task-Oriented Dialogue