Conversational Bootstrapping and Other Tricks of a Concierge Robot

We describe the effective use of online learning to enhance the conversational capabilities of a concierge robot that we have been developing over the last two years. The robot was designed to interact naturally with visitors and uses a speech recognition system in conjunction with a natural language classifier. The online learning component monitors interactions and collects explicit and implicit user feedback from a conversation and feeds it back to the classifier in the form of new class instances and adjusted threshold values for triggering the classes. In addition, it enables a trusted master to teach it new question-answer pairs via question-answer paraphrasing, and solicits help with maintaining question-answer-class relationships when needed, obviating the need for explicit programming. The system has been completely implemented and demonstrated using the SoftBank Robotics [34] humanoid robots Pepper and NAO, and the telepresence robot known as Double from Double Robotics [4].

[1]  Thierry Dutoit,et al.  A probabilistic framework for dialog simulation and optimal strategy learning , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[2]  Luísa Coheur,et al.  From symbolic to sub-symbolic information in question classification , 2011, Artificial Intelligence Review.

[3]  Dan Roth,et al.  Learning to Resolve Natural Language Ambiguities: A Unified Approach , 1998, AAAI/IAAI.

[4]  Alexander I. Rudnicky,et al.  Miscommunication Recovery in Physically Situated Dialogue , 2015, SIGDIAL Conference.

[5]  Dan Roth,et al.  Learning question classifiers: the role of semantic information , 2005, Natural Language Engineering.

[6]  Konstantin Tretyakov,et al.  Machine Learning Techniques in Spam Filtering , 2004 .

[7]  Takayuki Kanda,et al.  An affective guide robot in a shopping mall , 2009, 2009 4th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[8]  Akira Shimazu,et al.  Subtree Mining for Question Classification Problem , 2007, IJCAI.

[9]  Jeffrey O. Kephart,et al.  Incremental Learning in SwiftFile , 2000, ICML.

[10]  Jennifer Chu-Carroll,et al.  Building Watson: An Overview of the DeepQA Project , 2010, AI Mag..

[11]  Walmir M. Caminhas,et al.  A review of machine learning approaches to Spam filtering , 2009, Expert Syst. Appl..

[12]  W. Bruce Croft,et al.  Analysis of Statistical Question Classification for Fact-Based Questions , 2005, Information Retrieval.

[13]  Jerome A. Feldman,et al.  Exploiting deep semantics and compositionality of natural language for Human-Robot-Interaction , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[14]  Sheikh Iqbal Ahamed,et al.  Applying affective feedback to reinforcement learning in ZOEI, a comic humanoid robot , 2014, The 23rd IEEE International Symposium on Robot and Human Interactive Communication.

[15]  Fabrizio Sebastiani,et al.  Machine learning in automated text categorization , 2001, CSUR.

[16]  Roberto Pieraccini,et al.  Learning dialogue strategies within the Markov decision process framework , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[17]  Zengchang Qin,et al.  Question Classification using Head Words and their Hypernyms , 2008, EMNLP.

[18]  References , 1971 .

[19]  Marilyn A. Walker,et al.  Reinforcement Learning for Spoken Dialogue Systems , 1999, NIPS.

[20]  Florence March,et al.  2016 , 2016, Affair of the Heart.

[21]  Avelino J. Gonzalez,et al.  Towards a method for evaluating naturalness in conversational dialog systems , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[22]  David A. Hull.  Xerox TREC-8 Question Answering Track Report , 1999, TREC.

[23]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[24]  Jerome A. Feldman,et al.  Embodied Construction Grammar , 2009 .

[25]  Ellen Dodge,et al.  A Neural Theory of Language and Embodied Construction Grammar , 2008 .

[26]  Dragomir R. Radev,et al.  The Use of Predictive Annotation for Question Answering in TREC8 , 1999, TREC.

[27]  Reid G. Simmons,et al.  Interactions with a moody robot , 2006, HRI '06.

[28]  Asli Çelikyilmaz,et al.  Investigation of Question Classifier in Question Answering , 2009, EMNLP.

[29]  Wolfram Burgard,et al.  The Interactive Museum Tour-Guide Robot , 1998, AAAI/IAAI.

[30]  Santosh Kumar Ray,et al.  A semantic approach for question classification using WordNet and Wikipedia , 2010, Pattern Recognit. Lett..

[31]  Sharath Pankanti,et al.  An Extensible Language Interfacefor Robot Manipulation , 2012, AGI.