Statistical shared plan-based dialog management

In this paper we describe a statistical shared plan-based approach to dialog modeling and dialog management. We apply this approach to a corpus of human-human spoken dialogs. We compare the performance of models trained on transcribed and automatically recognized speech, and present ideas for further improving the models.

[1]  Anne H. Anderson,et al.  The Hcrc Map Task Corpus , 1991 .

[2]  Barbara Di Eugenio,et al.  FLSA: Extending Latent Semantic Analysis with Features for Dialogue Act Classification , 2004, ACL.

[3]  Massimo Poesio,et al.  The predictive power of game structure in dialogue act recognition: experimental results using maximum entropy estimation , 1998, ICSLP.

[4]  Srinivas Bangalore,et al.  Where do thewords come from? Learning models for word choice and ordering from spoken dialog corpora , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  Srinivas Bangalore,et al.  Towards Learning to Converse: Structuring Task-Oriented Human-Human Dialogs , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[6]  Srinivas Bangalore,et al.  Supertagging: An Approach to Almost Parsing , 1999, CL.

[7]  P Taylor,et al.  Intonation and dialogue context as constraints for speech recognition , 1998 .

[8]  Dilek Z. Hakkani-Tür,et al.  The AT&T WATSON speech recognizer , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[9]  Steve J. Young,et al.  Partially observable Markov decision processes for spoken dialog systems , 2007, Comput. Speech Lang..

[10]  Tomek Strzalkowski,et al.  Data-Driven Strategies for an Automated Dialogue System , 2004, ACL.

[11]  Karen E. Lochbaum,et al.  A Collaborative Planning Model of Intentional Structure , 1998, CL.

[12]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.

[13]  Andrej Ljolje.  Multiple task-domain acoustic models , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[14]  Oliver Lemon,et al.  Reinforcement learning of dialogue strategies using the user's last dialogue act , 2005 .

[15]  Kallirroi Georgila,et al.  Hybrid reinforcement/supervised learning for dialogue policies from COMMUNICATOR data , 2005 .