Abstract
Recent studies show that user simulations can be used to generate training corpora for learning dialogue strategies automatically. However, it is unclear what type of simulation is most suitable in a particular task setting. We observe that a simulation which generates random behaviors in a restricted way outperforms simulations that mimic human user behaviors in a statistical way. Our finding suggests that we do not always need to construct a realistic user simulation. Since constructing realistic user simulations is not a trivial task, we can save engineering cost by wisely choosing simulation models that are appropriate for our task.
- Ai, H. and Litman, D. 2007. Knowledge consistent user simulations for dialog systems. In Proceedings of Interspeech.Google Scholar
- Ai, H. and Litman, D. 2008. Assessing dialog system user simulation evaluation measures using human judges. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics.Google Scholar
- Ai, H. and Litman, D. 2009. Setting up user action probabilities in user simulations for dialog system development. In Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics. Google ScholarDigital Library
- Ai, H., Raux, A., Borus, D., Exkenazi, M., and Litman, D. 2007. Comparing spoken dialog corpora collected with recruited subjects versus real users. In Proceedings of the 8th SIGDial Workshop on Discourse and Dialog.Google Scholar
- Ai, H., Tetreault, J., and Litman, D. 2007. Comparing user simulation models for dialog strategy learning. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics. Google ScholarDigital Library
- Forbes-Riley, K. and Litman, D. 2005. Using Bigrams to Identify Relationships Between Student Certainness States and Tutor Responses in a Spoken Dialogue Corpus. In Proceedings of SIGdial.Google Scholar
- Forbes-Riley, K., Litman, D., and Rotaru, M. 2008. Responding to student uncertainty during computer tutoring: An experimental evaluation. In Proceedings of the 9th International Conference on Intelligent Tutoring Systems (ITS). Google ScholarDigital Library
- Forbes-Riley, K., Litman, D., Silliman, S., and Tetreault, J. 2006. Comparing synthesized versus pre-recorded tutor speech in an intelligent tutoring spoken dialog system. In Proceedings of the 19th International FLAIRS (Florida Artificial Intelligence Research Society) Conference.Google Scholar
- Georgila, K., Henderson, J., and Lemon, O. 2006. User simulation for spoken dialog systems: Learning and evaluation. In Proceedings of Interspeech.Google Scholar
- Georgila, K., Wolters, M., and Moore, J. 2008. Simulating the behavior of older versus younger users when interacting with spoken dialog systems. In Proceedings of the 46th Annual Conference of Association of Computational Linguistics. Google ScholarDigital Library
- Henderson, J., Lemon, O., and Georgila, K. 2005. Hybrid reinforcement/supervised learning for dialog policies from COMMUNICATOR data. In Proceedings of the IJCAI Workshop on Knowledge and Reasoning in Practical Dialog Systems.Google Scholar
- Horvitz, E. and Paek, T. 1999. A computational architecture for conversation. In Proceedings of the 7th International Conference on User Modeling. Google ScholarDigital Library
- Janarthanam, S. and Lemon, O. 2008. User simulations for online adaptation and knowledge-alignment in troubleshooting dialog systems. In Proceedings of the 12th SEMdial Workshop on on the Semantics and Pragmatics of Dialogs.Google Scholar
- Lemon, O. and Pietquin, O. 2007. Machine learning for spoken dialog systems. In Proceedings of Interspeech 2007.Google Scholar
- Lemon, O., Georgila, K., and Henderson, J. 2006. Evaluating effectiveness and portability of reinforcement learned dialog strategies with real users: The TALK TownInfo evaluation. In Proceedings of IEEE/ACL Spoken Language Technology Workshop.Google Scholar
- Lemon, O. and Liu, X. 2007. Dialog policy learning for combinations of noise and user Simulation: transfer results. In Proceedings of the SIGdial Workshop.Google Scholar
- Levin, E., Pieraccini, R., and Eckert, W. 2000. A stochastic model of human-machine interaction for learning dialog strategies. IEEE Trans. Speech Audio Proces. 8, 1, 11.Google ScholarCross Ref
- Litman, D. and Silliman, S. 2004. ITSPOKE: An intelligent tutoring spoken dialog system. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics. Google ScholarDigital Library
- Litman, D., Rose, C., Forbes-Riley, K., Vanlehn, K., Bhembe, D., and Silliman, S. 2004. Spoken versus typed human and computer dialog tutoring. In Proceedings of the 7th International Conference on Intelligent Tutoring Systems (ITS).Google Scholar
- Paek, T. 2006. Reinforcement learning for spoken dialog systems: Comparing strengths and weaknesses for practical deployment. In Proceeding of the Interspeech Workshop on Dialog on Dialogs Multidisciplinary Evaluation of Advanced Speech-Based Interactive Systems.Google Scholar
- Rieser, V. and Lemon, O. 2006. Cluster-based user simulations for learning dialog strategies. In Proceedings of Interspeech.Google Scholar
- Rotaru, M. 2008. Applications of discourse structure for spoken dialog systems. Ph.D. Dissertation, University of Pittsburgh. Google ScholarDigital Library
- Schatzmann, J., Georgila, K., and Young, S. 2005. Quantitative evaluation of user simulation techniques for spoken dialog systems. In Proceedings of the 6th SIGdial Workshop on Discourse and Dialog.Google Scholar
- Schatzmann, J., Thomson, B., Weilhammer, K., Ye, H., and Young. S. 2007. Agenda-based user simulation for bootstrapping a POMDP dialog system. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics—Human Language Technologies (NAACL-HLT'07). Google ScholarDigital Library
- Schatzmann, J., Weilhammer, K., Stuttle, M., and Young, S. 2006. A survey of statistical user simulation techniques for reinforcement-learning of dialog management strategies. Knowl. Engin. Rev. 21, 2. Google ScholarDigital Library
- Singh, S., Litman, D., Kearns, M., and Walker, M. 2002. Optimizing dialog managment with reinforcement learning: Experiments with the NJFun system. J. Artif. Intel. Resear. Google ScholarDigital Library
- Sutton, R. and Barto, A. 1998. Reinforcement Learning. MIT Press. Google ScholarDigital Library
- Tetreault, J. and Litman, D. 2006. Comparing the utility of state features in spoken dialog using reinforcement learning. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics—Human Language Technologies (NAACL-HLT'06). Google ScholarDigital Library
- Tetreault, J., Bohus, D., and Litman, D. 2007. Estimating the reliability of MDP Policies; A confidence interval approach. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics—Human Language Technologies (NAACL-HLT'07).Google Scholar
- Vanlehn, K., Jordan, P. W., Roe, C. P., Bhembe, D., Bottner, M., Gaydos, A., Makatchev, M., Pappuswamy, U., Ringenberg, M., Roque, A., Siler, S., Srivastava, R., and Wilson, R. 2002. The architecture ofWhy2-Atlas; A coach for qualitative physics essay writing. In Proceedings of the Intelligent Tutoring Systems Conference. Google ScholarDigital Library
- Williams, J. and Young, S. 2007. Partially observable Markov decision processes for spoken dialog systems. Comput. Speech Lang. 21, 2. Google ScholarDigital Library
Index Terms
- Comparing user simulations for dialogue strategy learning
Recommendations
Hybrid user intention modeling to diversify dialog simulations
This paper proposes a novel user intention simulation method which is data-driven but can integrate diverse user discourse knowledge to simulate various types of user behaviors. A method of data-driven user intention modeling based on logistic ...
EmoUS: Simulating User Emotions in Task-Oriented Dialogues
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalExisting user simulators (USs) for task-oriented dialogue systems only model user behaviour on semantic and natural language levels without considering the user persona and emotions. Optimising dialogue systems with generic user policies, which cannot ...
User simulation in a stochastic dialog system
We present a new methodology of user simulation applied to the evaluation and refinement of stochastic dialog systems. Common weaknesses of these systems are the scarceness of the training corpus and the cost of an evaluation made by real users. We have ...
Comments