%0 Generic %1 li2016simulator %A Li, Xiujun %A Lipton, Zachary C. %A Dhingra, Bhuwan %A Li, Lihong %A Gao, Jianfeng %A Chen, Yun-Nung %D 2016 %K chatbot machinelearning nlp %T A User Simulator for Task-Completion Dialogues %U http://arxiv.org/abs/1612.05688 %X Despite widespread interests in reinforcement-learning for task-oriented dialogue systems, several obstacles can frustrate research and development progress. First, reinforcement learners typically require interaction with the environment, so conventional dialogue corpora cannot be used directly. Second, each task presents specific challenges, requiring separate corpus of task-specific annotated data. Third, collecting and annotating human-machine or human-human conversations for task-oriented dialogues requires extensive domain knowledge. Because building an appropriate dataset can be both financially costly and time-consuming, one popular approach is to build a user simulator based upon a corpus of example dialogues. Then, one can train reinforcement learning agents in an online fashion as they interact with the simulator. Dialogue agents trained on these simulators can serve as an effective starting point. Once agents master the simulator, they may be deployed in a real environment to interact with humans, and continue to be trained online. To ease empirical algorithmic comparisons in dialogues, this paper introduces a new, publicly available simulation framework, where our simulator, designed for the movie-booking domain, leverages both rules and collected data. The simulator supports two tasks: movie ticket booking and movie seeking. Finally, we demonstrate several agents and detail the procedure to add and test your own agent in the proposed framework.

@electronic{li2016simulator, abstract = {Despite widespread interests in reinforcement-learning for task-oriented dialogue systems, several obstacles can frustrate research and development progress. First, reinforcement learners typically require interaction with the environment, so conventional dialogue corpora cannot be used directly. Second, each task presents specific challenges, requiring separate corpus of task-specific annotated data. Third, collecting and annotating human-machine or human-human conversations for task-oriented dialogues requires extensive domain knowledge. Because building an appropriate dataset can be both financially costly and time-consuming, one popular approach is to build a user simulator based upon a corpus of example dialogues. Then, one can train reinforcement learning agents in an online fashion as they interact with the simulator. Dialogue agents trained on these simulators can serve as an effective starting point. Once agents master the simulator, they may be deployed in a real environment to interact with humans, and continue to be trained online. To ease empirical algorithmic comparisons in dialogues, this paper introduces a new, publicly available simulation framework, where our simulator, designed for the movie-booking domain, leverages both rules and collected data. The simulator supports two tasks: movie ticket booking and movie seeking. Finally, we demonstrate several agents and detail the procedure to add and test your own agent in the proposed framework.}, added-at = {2017-03-09T07:28:43.000+0100}, author = {Li, Xiujun and Lipton, Zachary C. and Dhingra, Bhuwan and Li, Lihong and Gao, Jianfeng and Chen, Yun-Nung}, biburl = {https://www.bibsonomy.org/bibtex/2898574d8c6a1cd9ba131f68612a714a2/winterdawn}, description = {A User Simulator for Task-Completion Dialogues}, interhash = {80aaa13e0cb285327580819e6ce3fca8}, intrahash = {898574d8c6a1cd9ba131f68612a714a2}, keywords = {chatbot machinelearning nlp}, note = {cite arxiv:1612.05688Comment: 14 pages}, timestamp = {2017-03-09T07:28:43.000+0100}, title = {A User Simulator for Task-Completion Dialogues}, url = {http://arxiv.org/abs/1612.05688}, year = 2016 }