Learning the Structure of Task-Driven Human-Human Dialogs

Data-driven techniques have been used for many computational linguistics tasks. Models derived from data are generally more robust than hand-crafted systems since they better reflect the distribution of the phenomena being modeled. With the availability of large corpora of spoken dialog, dialog management is now reaping the benefits of data-driven techniques. In this paper, we compare two approaches to modeling subtask structure in dialog: a chunk-based model of subdialog sequences, and a parse-based, or hierarchical, model. We evaluate these models using customer agent dialogs from a catalog service domain.

[1]  John Bear,et al.  Integrating Multiple Knowledge Sources for Detection and Correction of Repairs in Human-Computer Dialog , 1992, ACL.

[2]  Hung Hai Bui,et al.  A General Model for Online Probabilistic Plan Recognition , 2003, IJCAI.

[3]  Oliver Lemon,et al.  multithreaded context for robust conversational interfaces: Context-sensitive speech recognition and interpretation of corrective fragments , 2004, TCHI.

[4]  Candace L. Sidner,et al.  Attention, Intentions, and the Structure of Discourse , 1986, CL.

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

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

[7]  Sandra Carberry,et al.  Techniques for Plan Recognition , 2001, User Modeling and User-Adapted Interaction.

[8]  Roberto Pieraccini,et al.  A stochastic model of computer-human interaction for learning dialogue strategies , 1997, EUROSPEECH.

[9]  Mark G. Core.  Analyzing and Predicting Patterns of DAMSL Utterance Tags , 2002 .

[10]  Norbert Reithinger,et al.  Learning dialogue structures from a corpus , 1997, EUROSPEECH.

[11]  Steve Young,et al.  Automatic learning of dialogue strategy using dialogue simulation and reinforcement learning , 2002 .

[12]  Gökhan Tür,et al.  Prosody-based automatic segmentation of speech into sentences and topics , 2000, Speech Commun..

[13]  Srinivas Bangalore,et al.  Extracting clauses in dialogue corpora: Applications to spoken language understanding , 2004 .

[14]  Pascal Poupart,et al.  Partially Observable Markov Decision Processes with Continuous Observations for Dialogue Management , 2008, SIGDIAL.

[15]  Oliver Lemon,et al.  DIPPER: Description and Formalisation of an Information-State Update Dialogue System Architecture , 2003, SIGDIAL Workshop.

[16]  Eugene Charniak,et al.  Edit Detection and Parsing for Transcribed Speech , 2001, NAACL.

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

[18]  Gwyneth Doherty-Sneddon,et al.  The Reliability of a Dialogue Structure Coding Scheme , 1997, CL.

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

[20]  Brian Roark,et al.  Probabilistic Top-Down Parsing and Language Modeling , 2001, CL.

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

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

[23]  Candace L. Sidner,et al.  Plan parsing for intended response recognition in discourse 1 , 1985, Comput. Intell..

[24]  Patrick Haffner,et al.  Scaling large margin classifiers for spoken language understanding , 2006, Speech Commun..

[25]  J.G. Wilpon,et al.  Intelligent virtual agents for contact center automation , 2005, IEEE Signal Processing Magazine.

[26]  Andreas Stolcke,et al.  Dialogue act modeling for automatic tagging and recognition of conversational speech , 2000, CL.

[27]  Michael P. Wellman,et al.  Probabilistic State-Dependent Grammars for Plan Recognition , 2000, UAI.

[28]  James F. Allen,et al.  A Plan Recognition Model for Subdialogues in Conversations , 1987, Cogn. Sci..

[29]  Helen F. Hastie,et al.  Automatically predicting dialogue structure using prosodic features , 2002, Speech Commun..

[30]  Candace L. Sidner,et al.  COLLAGEN: when agents collaborate with people , 1997, AGENTS '97.

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

[32]  S. Singh,et al.  Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System , 2011, J. Artif. Intell. Res..

[33]  Stephanie Seneff.  A relaxation method for understanding spontaneous speech utterances , 1992 .

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

[35]  Alexander I. Rudnicky,et al.  Ravenclaw: dialog management using hierarchical task decomposition and an expectation agenda , 2003, INTERSPEECH.

[36]  Giuseppe Di Fabbrizio,et al.  Florence: a dialogue manager framework for spoken dialogue systems , 2004, INTERSPEECH.

[37]  Ken Samuel,et al.  Computing Dialogue Acts from Features with Transformation-Based Learning , 1998, ArXiv.