DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues

Abstract

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.

arXiv commentAccepted at ICLR 2021; https://openreview.net/forum?id=kDnal_bbb-E

References in corpus (7)

• A Neural Conversational Model
• Hierarchical Graph Pooling with Structure Learning
• HiGRU: Hierarchical Gated Recurrent Units for Utterance-level Emotion Recognition
• Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
• Unsupervised Dialog Structure Learning
• Combining Search with Structured Data to Create a More Engaging User Experience in Open Domain Dialogue
• Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture