arXiv (Cornell University) · 2018 · 11 citations · 22 references
ComputingComputer ScienceStrategyArtificial IntelligenceNatural Language ProcessingNegotiationConversational InterfacesConversational User InterfacesDialogue SystemsNegotiation ProcessNegotiation StrategyReinforcement LearningConversational AgentsDialog SystemsNatural Language InterfacesNegotiation DialogueRetrieval-augmented GenerationRetrieval-based Response GenerationTask Success RateTask-oriented Dialogue
We consider negotiation settings in which two agents use natural language to bargain on goods. Agents need to decide on both high-level strategy (e.g., proposing \$50) and the execution of that strategy (e.g., generating "The bike is brand new. Selling for just \$50."). Recent work on negotiation trains neural models, but their end-to-end nature makes it hard to control their strategy, and reinforcement learning tends to lead to degenerate solutions. In this paper, we propose a modular approach based on coarse di- alogue acts (e.g., propose(price=50)) that decouples strategy and generation. We show that we can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy, while our retrieval-based generation can maintain context-awareness and produce diverse utterances. We test our approach on the recently proposed DEALORNODEAL game, and we also collect a richer dataset based on real items on Craigslist. Human evaluation shows that our systems achieve higher task success rate and more human-like negotiation behavior than previous approaches.
22
A Network-based End-to-End Trainable Task-oriented Dialogue System
Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić et al. · 2017 · 806 citations · Full text
Deep Reinforcement Learning for Dialogue Generation
Jiwei Li, Will Monroe, Alan Ritter et al. · arXiv (Cornell University) · 2016 · 421 citations · Full text