Decoupling Strategy and Generation in Negotiation Dialogues

He He, Derek Chen, Anusha Balakrishnan, Percy Liang


Abstract
We consider negotiation settings in which two agents use natural language to bargain on goods. Agents need to decide on both high-level strategy (e.g., proposing $50) and the execution of that strategy (e.g., generating “The bike is brand new. Selling for just $50!”). Recent work on negotiation trains neural models, but their end-to-end nature makes it hard to control their strategy, and reinforcement learning tends to lead to degenerate solutions. In this paper, we propose a modular approach based on coarse dialogue acts (e.g., propose(price=50)) that decouples strategy and generation. We show that we can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy, while our retrieval-based generation can maintain context-awareness and produce diverse utterances. We test our approach on the recently proposed DEALORNODEAL game, and we also collect a richer dataset based on real items on Craigslist. Human evaluation shows that our systems achieve higher task success rate and more human-like negotiation behavior than previous approaches.
Anthology ID:
D18-1256
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2333–2343
Language:
URL:
https://www.aclweb.org/anthology/D18-1256
DOI:
10.18653/v1/D18-1256
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D18-1256.pdf
Attachment:
 D18-1256.Attachment.pdf
Video:
 https://vimeo.com/305940786