Agreement Tracking for Multi-Issue Negotiation Dialogues

TL;DR

This paper introduces a new task of agreement tracking in multi-issue negotiations, creating a synthetic dataset and baseline models to facilitate research in structured agreement monitoring.

Contribution

It defines agreement tracking for multi-issue negotiations, develops GPT-Negochat dataset, and demonstrates transfer learning with T5 models to improve tracking accuracy.

Findings

Pre-training T5 on MultiWOZ improves results by up to 21%.

GPT-Negochat dataset is publicly available for research.

Transfer learning enhances agreement tracking performance.

Abstract

Automated negotiation support systems aim to help human negotiators reach more favorable outcomes in multi-issue negotiations (e.g., an employer and a candidate negotiating over issues such as salary, hours, and promotions before a job offer). To be successful, these systems must accurately track agreements reached by participants in real-time. Existing approaches either focus on task-oriented dialogues or produce unstructured outputs, rendering them unsuitable for this objective. Our work introduces the novel task of agreement tracking for two-party multi-issue negotiations, which requires continuous monitoring of agreements within a structured state space. To address the scarcity of annotated corpora with realistic multi-issue negotiation dialogues, we use GPT-3 to build GPT-Negochat, a synthesized dataset that we make publicly available. We present a strong initial baseline for our task by transfer-learning a T5 model trained on the MultiWOZ 2.4 corpus. Pre-training T5-small and T5-base on MultiWOZ 2.4's DST task enhances results by 21% and 9% respectively over training solely on GPT-Negochat. We validate our method's sample-efficiency via smaller training subset experiments. By releasing GPT-Negochat and our baseline models, we aim to encourage further research in multi-issue negotiation dialogue agreement tracking.