Improving Dialog Systems for Negotiation with Personality Modeling


Abstract in English

In this paper, we explore the ability to model and infer personality types of opponents, predict their responses, and use this information to adapt a dialog agents high-level strategy in negotiation tasks. Inspired by the idea of incorporating a theory of mind (ToM) into machines, we introduce a probabilistic formulation to encapsulate the opponents personality type during both learning and inference. We test our approach on the CraigslistBargain dataset and show that our method using ToM inference achieves a 20% higher dialog agreement rate compared to baselines on a mixed population of opponents. We also find that our model displays diverse negotiation behavior with different types of opponents.

Download