September 8, 2017
Deal or No Deal? End-to-End Learning for Negotiation Dialogues
Conference on Empirical Methods on Natural Language Processing (EMNLP)
Negotiations require complex communication and reasoning skills, but success is easy to measure, making this an interesting task for AI. We gather a large dataset of human-human negotiations on a multi-issue bargaining task, where agents who cannot observe each other’s reward functions must reach an agreement (or a deal) via natural language dialogue. For the first time, we show it is possible to train end-to-end models for negotiation, which must learn both linguistic and reasoning skills with no annotated dialogue states.
By: Mike Lewis, Denis Yarats, Yann Dauphin, Devi Parikh, Dhruv Batra
Facebook AI Research