Learning User Intentions Spanning Multiple Domains

People are able to interact with domain-specific applications in smart environments and get assistance with specific tasks. Current intelligent agents (IAs) tend to be limited to specific applications. In order to engage in more complex activities users have to directly manage a task that may span multiple applications. An ideal personal IA would be able to learn, over time, about these tasks that span different resources. This paper addresses the problem of multi-domain task assistance in the context of spoken dialog systems. We propose approaches to discover users’ high-level intentions and using this information to assist users in their task. We collected real-life smart phone usage data from 14 participants and investigated how to extract high-level intents from users’ descriptions of their activities. Our experiments show that understanding high-level tasks allows the agent to actively suggest apps relevant to pursuing particular user goals and reduce the cost of users’ self-management. Author

[1]  Hiroshi G. Okuno,et al.  A Two-Stage Domain Selection Framework for Extensible Multi-Domain Spoken Dialogue Systems , 2011, SIGDIAL Conference.

[2]  Gökhan Tür,et al.  Distributed open-domain conversational understanding framework with domain independent extractors , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[3]  Alexander I. Rudnicky,et al.  Matrix Factorization with Domain Knowledge and Behavioral Patterns for Intent Modeling , 2015 .

[4]  Alexander I. Rudnicky,et al.  Learning OOV through semantic relatedness in spoken dialog systems , 2015, INTERSPEECH.

[5]  Alexander I. Rudnicky,et al.  Leveraging Behavioral Patterns of Mobile Applications for Personalized Spoken Language Understanding , 2015, ICMI.

[6]  Alexander I. Rudnicky,et al.  Instruction Taking in the TeamTalk System , 2010, AAAI Fall Symposium: Dialog with Robots.

[7]  Alexander I. Rudnicky,et al.  Spoken language interfaces: the OM system , 1991, CHI.

[8]  Maxine Eskénazi,et al.  LET's GO: improving spoken dialog systems for the elderly and non-natives , 2003, INTERSPEECH.

[9]  Robert Xiao,et al.  TouchTools: leveraging familiarity and skill with physical tools to augment touch interaction , 2014, CHI.

[10]  Alexander I. Rudnicky,et al.  AppDialogue: Multi-App Dialogues for Intelligent Assistants , 2016, LREC.

[11]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[12]  Alexander I. Rudnicky,et al.  An Intelligent Assistant for High-Level Task Understanding , 2016, IUI.

[13]  Lin-Shan Lee,et al.  A DISTRIBUTED ARCHITECTURE FOR COOPERATIVE SPOKEN DIALOGUE AGENTS WITH COHERENT DIALOGUE STATE AND HISTORY , 2000 .

[14]  Michael W. Berry,et al.  Text mining : applications and theory , 2010 .

[15]  Alexander I. Rudnicky,et al.  Dynamically supporting unexplored domains in conversational interactions by enriching semantics with neural word embeddings , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[16]  Gary Geunbae Lee,et al.  Detecting Multiple Domains from User's Utterance in Spoken Dialog System , 2015, Natural Language Dialog Systems and Intelligent Assistants.

[17]  Robert Tibshirani,et al.  Estimating the number of clusters in a data set via the gap statistic , 2000 .

[18]  Alexander I. Rudnicky,et al.  Understanding User ’ s Cross-Domain Intentions in Spoken Dialog Systems , 2015 .

[19]  Helen F. Hastie,et al.  The PARLANCE mobile application for interactive search in English and Mandarin , 2014, SIGDIAL Conference.

[20]  Alexander I. Rudnicky,et al.  Situated Multiparty Interaction between Humans and Agents , 2013, HCI.

[21]  Alexander I. Rudnicky,et al.  Spoken language recognition in an office management domain , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[22]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[23]  Anette Hulth,et al.  Improved Automatic Keyword Extraction Given More Linguistic Knowledge , 2003, EMNLP.

[24]  Jonathan G. Fiscus,et al.  A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER) , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[25]  Steve J. Young,et al.  USING POMDPS FOR DIALOG MANAGEMENT , 2006, 2006 IEEE Spoken Language Technology Workshop.

[26]  Alexander I. Rudnicky,et al.  Unsupervised user intent modeling by feature-enriched matrix factorization , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[27]  Amos Azaria,et al.  Instructable Intelligent Personal Agent , 2016, AAAI.

[28]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[29]  Mitchell P. Marcus,et al.  Text Chunking using Transformation-Based Learning , 1995, VLC@ACL.

[30]  Alexander I. Rudnicky,et al.  HELPR: A Framework to Break the Barrier Across Domains in Spoken Dialog Systems , 2016, IWSDS.