I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents
arXiv:2002.02878
Abstract
Dialogue research tends to distinguish between chit-chat and goal-oriented tasks. While the former is arguably more naturalistic and has a wider use of language, the latter has clearer metrics and a straightforward learning signal. Humans effortlessly combine the two, for example engaging in chit-chat with the goal of exchanging information or eliciting a specific response. Here, we bridge the divide between these two domains in the setting of a rich multi-player text-based fantasy environment where agents and humans engage in both actions and dialogue. Specifically, we train a goal-oriented model with reinforcement learning against an imitation-learned ``chit-chat'' model with two approaches: the policy either learns to pick a topic or learns to pick an utterance given the top-K utterances from the chit-chat model. We show that both models outperform an inverse model baseline and can converse naturally with their dialogue partner in order to achieve goals.
References in corpus (13)
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- Deep Reinforcement Learning for Dialogue Generation
- Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
- Personalizing Dialogue Agents: I have a dog, do you have pets too?
- A Persona-Based Neural Conversation Model
- Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
- Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
- Language Understanding for Text-based Games Using Deep Reinforcement Learning
- TextWorld: A Learning Environment for Text-based Games
- ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons
- Hierarchical Decision Making by Generating and Following Natural Language Instructions
- Learning Semantic Textual Similarity from Conversations
- Training Millions of Personalized Dialogue Agents