End-to-End Trainable Non-Collaborative Dialog System


  • Yu Li University of California, Davis
  • Kun Qian University of California, Davis
  • Weiyan Shi University of California, Davis
  • Zhou Yu University of California, Davis




End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task. While in non-collaborative settings, for example, negotiation and persuasion, users and systems do not share a common goal. As a result, compared to collaborate tasks, people use social content to build rapport and trust in these non-collaborative settings in order to advance their goals. To handle social content, we introduce a hierarchical intent annotation scheme, which can be generalized to different non-collaborative dialog tasks. Building upon TransferTransfo (Wolf et al. 2019), we propose an end-to-end neural network model to generate diverse coherent responses. Our model utilizes intent and semantic slots as the intermediate sentence representation to guide the generation process. In addition, we design a filter to select appropriate responses based on whether these intermediate representations fit the designed task and conversation constraints. Our non-collaborative dialog model guides users to complete the task while simultaneously keeps them engaged. We test our approach on our newly proposed AntiScam dataset and an existing PersuasionForGood dataset. Both automatic and human evaluations suggest that our model outperforms multiple baselines in these two non-collaborative tasks.




How to Cite

Li, Y., Qian, K., Shi, W., & Yu, Z. (2020). End-to-End Trainable Non-Collaborative Dialog System. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 8293-8302. https://doi.org/10.1609/aaai.v34i05.6345



AAAI Technical Track: Natural Language Processing