Mining mixed-initiative dialogs

Human-computer dialogs are an important vehicle through which to produce a rich and compelling form of human-computer interaction. We view the specification of a human-computer dialog as a set of sequences of progressive interactions between a user and a computer system, and mine partially ordered sets, which correspond to mixing dialog initiative, embedded in these sets of sequences—a process we refer to as dialog mining—because partially ordered sets can be advantageously exploited to reduce the control complexity of a dialog implementation. Our mining losslessly compresses the specification of a dialog. We describe our mining algorithm and report the results of a simulation-oriented evaluation. Our algorithm is sound, and our results indicate that it can compress nearly all dialog specifications, and some to a high degree. This work is part of broader research on the specification and implementation of mixed-initiative dialogs.

[1]  Jennifer Chu-Carroll,et al.  MIMIC: An Adaptive Mixed Initiative Spoken Dialogue System for Information Queries , 2000, ANLP.

[2]  S. Kronenberg,et al.  Bridging the gap between mixed-initiative dialogs and reusable sub-dialogs , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

[3]  Michael English,et al.  Learning Mixed Initiative Dialog Strategies By Using Reinforcement Learning On Both Conversants , 2005, HLT.

[4]  James R. Glass,et al.  Flexible and Personalizable Mixed-Initiative Dialogue Systems , 2003, HLT-NAACL 2003.

[5]  R. Bryce Inouye.  Minimizing the Length of Non-Mixed Initiative Dialogs , 2004, ACL.

[6]  Anton Leuski,et al.  Creating Conversational Characters Using Question Generation Tools , 2012, Dialogue Discourse.

[7]  Manuel A. Pérez-Quiñones,et al.  The Staging Transformation Approach to Mixing Initiative , 2003, IJCAI 2003.

[8]  Michael L. Scott,et al.  Programming Language Pragmatics , 1999 .

[9]  Neil D. Jones,et al.  An introduction to partial evaluation , 1996, CSUR.

[10]  Joseph Polifroni,et al.  Towards the automatic generation of mixed-initiative dialogue systems from web content , 2003, INTERSPEECH.

[11]  Kallirroi Georgila,et al.  Reinforcement Learning of Question-Answering Dialogue Policies for Virtual Museum Guides , 2012, SIGDIAL Conference.

[12]  Christian Queinnec.  Lisp in small pieces , 1994 .

[13]  Marilyn A. Walker,et al.  Mixed Initiative in Dialogue: An Investigation into Discourse Segmentation , 1990, ACL.

[14]  Kenji Mase,et al.  Interaction pattern and motif mining method for doctor-patient multi-modal dialog analysis , 2009, ICMI-MLMI '09.

[15]  Naren Ramakrishnan,et al.  Mixed-initiative interaction = mixed computation , 2001, PEPM '02.

[16]  Victor Zue,et al.  Conversational interfaces: advances and challenges , 1997, Proceedings of the IEEE.

[17]  Lin Padgham,et al.  Mixed-initiative conversational system using question-answer pairs mined from the web , 2012, CIKM '12.

[18]  Periklis Andritsos,et al.  Constructing adaptive configuration dialogs using crowd data , 2014, ASE.

[19]  Dilek Z. Hakkani-Tür,et al.  Mining Spoken Dialogue Corpora for System Evaluation and Modelin , 2004, EMNLP.

[20]  Dilek Z. Hakkani-Tür,et al.  Webtalk: Towards Automatically Building Spoken Dialog Systems Through Miningwebsites , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[21]  Gökhan Tür,et al.  Mining Search Query Logs for Spoken Language Understanding , 2012, SDCTD@NAACL-HLT.

[22]  Curry Guinn,et al.  Mixed-initiative interaction , 1999 .

[23]  Gary Geunbae Lee,et al.  Recent Approaches to Dialog Management for Spoken Dialog Systems , 2010, J. Comput. Sci. Eng..

[24]  Saverio Perugini,et al.  A language-based model for specifying and staging mixed-initiative dialogs , 2016, EICS.

[25]  Mitchell Wand,et al.  Essentials of Programming Languages, 3rd Edition , 2008 .