Are You Asking the Right Questions? Teaching Machines to Ask Clarification Questions

Inquiry is fundamental to communication, and machines cannot effectively collaborate with humans unless they can ask questions. In this thesis work, we explore how can we teach machines to ask clarification questions when faced with uncertainty, a goal of increasing importance in today’s automated society. We do a preliminary study using data from StackExchange, a plentiful online resource where people routinely ask clarifying questions to posts so that they can better offer assistance to the original poster. We build neural network models inspired by the idea of the expected value of perfect information: a good question is one whose expected answer is going to be most useful. To build generalizable systems, we propose two future research directions: a template-based model and a sequence-to-sequence based neural generative model.

[1]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[2]  Joelle Pineau,et al.  How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation , 2016, EMNLP.

[3]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[4]  Vasile Rus,et al.  Question Generation Shared Task and Evaluation Challenge – Status Report , 2011, ENLG.

[5]  Mordecai Avriel,et al.  The Value of Information and Stochastic Programming , 1970, Oper. Res..

[6]  Matthew Purver.  The Theory and Use of Clarification Requests in Dialogue , 2004 .

[7]  Margaret Mitchell,et al.  Generating Natural Questions About an Image , 2016, ACL.

[8]  Xin Jiang,et al.  Neural Generative Question Answering , 2015, IJCAI.

[9]  Lucy Vanderwende.  The Importance of Being Important: Question Generation , 2008 .

[10]  Ming Liu,et al.  Automatic Question Generation for Literature Review Writing Support , 2010, Intelligent Tutoring Systems.

[11]  Luke S. Zettlemoyer,et al.  Bootstrapping Semantic Parsers from Conversations , 2011, EMNLP.

[12]  Jonathan Ginzburg,et al.  The Interactive Stance , 2012 .

[13]  Oriol Vinyals,et al.  Adversarial Evaluation of Dialogue Models , 2017, ArXiv.

[14]  Joelle Pineau,et al.  The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems , 2015, SIGDIAL Conference.

[15]  Igor Labutov,et al.  Deep Questions without Deep Understanding , 2015, ACL.

[16]  Noah A. Smith,et al.  Automatic factual question generation from text , 2011 .

[17]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[18]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.