Weakly supervised user intent detection for multi-domain dialogues

Users interact with mobile apps with certain intents such as finding a restaurant. Some intents and their corresponding activities are complex and may involve multiple apps; for example, a restaurant app, a messenger app and a calendar app may be needed to plan a dinner with friends. However, activities may be quite personal and third-party developers would not be building apps to specifically handle complex intents (e.g., a DinnerPlanner). Instead we want our intelligent agent to actively learn to understand these intents and provide assistance when needed. This paper proposes a framework to enable the agent to learn an inventory of intents from a small set of task-oriented user utterances. The experiments show that on previously unseen user activities, the agent is able to reliably recognize user intents using graph-based semi-supervised learning methods. The dataset, models, and the system outputs are available to research community.

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

[2]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[3]  Zoubin Ghahramani,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[4]  Delip Rao,et al.  Semi-Supervised Polarity Lexicon Induction , 2009, EACL.

[5]  Thorsten Joachims,et al.  Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.

[6]  Fabio Gagliardi Cozman,et al.  Semi-Supervised Learning of Mixture Models , 2003, ICML.

[7]  Shankar Kumar,et al.  Video suggestion and discovery for youtube: taking random walks through the view graph , 2008, WWW.

[8]  Petr Sojka,et al.  Software Framework for Topic Modelling with Large Corpora , 2010 .

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

[10]  Shih-Fu Chang,et al.  Graph construction and b-matching for semi-supervised learning , 2009, ICML '09.

[11]  Avrim Blum,et al.  Learning from Labeled and Unlabeled Data using Graph Mincuts , 2001, ICML.

[12]  Qiang Ma,et al.  App2Vec: Vector modeling of mobile apps and applications , 2016, 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[13]  Partha Pratim Talukdar,et al.  Automatic Gloss Finding for a Knowledge Base using Ontological Constraints , 2015, WSDM.

[14]  Zoubin Ghahramani,et al.  Learning from labeled and unlabeled data with label propagation , 2002 .

[15]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[16]  Olivier Ledoit,et al.  A well-conditioned estimator for large-dimensional covariance matrices , 2004 .

[17]  Jun Zhao,et al.  Collective entity linking in web text: a graph-based method , 2011, SIGIR.

[18]  Alexander I. Rudnicky,et al.  Predicting Tasks in Goal-Oriented Spoken Dialog Systems using Semantic Knowledge Bases , 2013, SIGDIAL Conference.

[19]  Derek Greene,et al.  Normalized Mutual Information to evaluate overlapping community finding algorithms , 2011, ArXiv.

[20]  Thorsten Joachims,et al.  Transductive Learning via Spectral Graph Partitioning , 2003, ICML.

[21]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

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

[23]  Eytan Domany,et al.  Semi-Supervised Learning -- A Statistical Physics Approach , 2006, ArXiv.

[24]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[25]  Koby Crammer,et al.  New Regularized Algorithms for Transductive Learning , 2009, ECML/PKDD.

[26]  Xiaojin Zhu,et al.  Introduction to Semi-Supervised Learning , 2009, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[27]  Alexander I. Rudnicky,et al.  Learning situated knowledge bases through dialog , 2014, INTERSPEECH.

[28]  Yoshua Bengio,et al.  Semi-supervised Learning by Entropy Minimization , 2004, CAP.