DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues

• DOI: 10.48550/arxiv.2106.00920
• Publication Date: 2021-01-01
• Authors: Joshi, Rishabh; Balachandran, Vid...; Vashishth, Shikhar; Black, Alan; Tsvetkov, Yulia
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Science - Computation and Language; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computation and Language (cs.CL); Machine Learning (cs.LG)

Accepted at ICLR 2021; https://openreview.net/forum?id=kDnal_bbb-E<br/>To successfully negotiate a deal, it is not enough to communicate fluently: pragmatic planning of persuasive negotiation strategies is essential. While modern dialogue agents excel at generating fluent sentences, they still lack pragmatic grounding and cannot reason strategically. We present DialoGraph, a negotiation system that incorporates pragmatic strategies in a negotiation dialogue using graph neural networks. DialoGraph explicitly incorporates dependencies between sequences of strategies to enable improved and interpretable prediction of next optimal strategies, given the dialogue context. Our graph-based method outperforms prior state-of-the-art negotiation models both in the accuracy of strategy/dialogue act prediction and in the quality of downstream dialogue response generation. We qualitatively show further benefits of learned strategy-graphs in providing explicit associations between effective negotiation strategies over the course of the dialogue, leading to interpretable and strategic dialogues.<br/>