Much of human dialogue occurs in semi-cooperative settings, where agents with different goals attempt to agree on common decisions. 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. We also introduce dialogue rollouts, in which the model plans ahead by simulating possible complete continuations of the conversation, and find that this technique dramatically improves performance.
Mike Lewis is a scientist at Facebook AI Research, working on connecting language and reasoning. Previously he was a postdoc at the University of Washington, developing search algorithms for neural structured prediction, and has a PhD from the University of Edinburgh on combining symbolic and distributed representations of meaning. He has won an Outstanding Submission Award at the 2014 ACL Workshop on Semantic Parsing, Best Paper at EMNLP 2016 and Best Resource Paper at ACL 2017. His work has been extensively covered in the media, with varying levels of accuracy, everywhere from New Scientist to the front page of The Sun.