2020/04/06 by Chawla, Kushal, Lucas, Gale, May, Jonathan +1
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #I.2.7
paper · doi:10.48550/arxiv.2004.02363
Agents that negotiate with humans find broad applications in pedagogy and conversational AI. Most efforts in human-agent negotiations rely on restrictive menu-driven interfaces for communication. To advance the research in language-based negotiation systems, we explore a novel task of early prediction of buyer-seller negotiation outcomes, by varying the fraction of utterances that the model can access. We explore the feasibility of early prediction by using traditional feature-based methods, as well as by incorporating the non-linguistic task context into a pretrained language model using sentence templates. We further quantify the extent to which linguistic features help in making better predictions apart from the task-specific price information. Finally, probing the pretrained model helps us to identify specific features, such as trust and agreement, that contribute to the prediction performance.