Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations

We investigate the problem of generating informative questions in information-asymmetric conversations. Unlike previous work on question generation which largely assumes knowledge of what the answer might be, we are interested in the scenario where the questioner is not given the context from which answers are drawn, but must reason pragmatically about how to acquire new information, given the shared conversation history. We identify two core challenges: (1) formally defining the informativeness of potential questions, and (2) exploring the prohibitively large space of potential questions to find the good candidates. To generate pragmatic questions, we use reinforcement learning to optimize an informativeness metric we propose, combined with a reward function designed to promote more specific questions. We demonstrate that the resulting pragmatic questioner substantially improves the informativeness and specificity of questions generated over a baseline model, as evaluated by our metrics as well as humans.

[1]  H. Grice Logic and conversation , 1975 .

[2]  B. Davey,et al.  Effects of question-generation training on reading comprehension , 1986 .

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

[4]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[5]  Robert van Rooy Questioning to Resolve Decision Problems , 2003 .

[6]  R. Mitkov,et al.  Computer-Aided Generation of Multiple-Choice Tests , 2003, International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003.

[7]  R. Rooij Questioning to resolve decision problems , 2003 .

[8]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[9]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[10]  Noah A. Smith,et al.  Good Question! Statistical Ranking for Question Generation , 2010, NAACL.

[11]  Paul Piwek,et al.  The First Question Generation Shared Task Evaluation Challenge , 2010, Dialogue Discourse.

[12]  Michael C. Frank,et al.  Predicting Pragmatic Reasoning in Language Games , 2012, Science.

[13]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

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

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[17]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[18]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.

[19]  Dan Klein,et al.  Reasoning about Pragmatics with Neural Listeners and Speakers , 2016, EMNLP.

[20]  Verena Rieser,et al.  Why We Need New Evaluation Metrics for NLG , 2017, EMNLP.

[21]  Francesca Gino,et al.  It Doesn’t Hurt to Ask: Question-Asking Increases Liking , 2017, Journal of personality and social psychology.

[22]  Joelle Pineau,et al.  Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses , 2017, ACL.

[23]  Ali Farhadi,et al.  Bidirectional Attention Flow for Machine Comprehension , 2016, ICLR.

[24]  Lior Wolf,et al.  Using the Output Embedding to Improve Language Models , 2016, EACL.

[25]  Vaibhava Goel,et al.  Self-Critical Sequence Training for Image Captioning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Xinya Du,et al.  Learning to Ask: Neural Question Generation for Reading Comprehension , 2017, ACL.

[27]  Ming Zhou,et al.  Neural Question Generation from Text: A Preliminary Study , 2017, NLPCC.

[28]  Christopher Potts,et al.  Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding , 2017, TACL.

[29]  Ming Zhou,et al.  Question Generation for Question Answering , 2017, EMNLP.

[30]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[31]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[32]  Alan Ritter,et al.  Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints , 2018, EMNLP.

[33]  Eunsol Choi,et al.  QuAC: Question Answering in Context , 2018, EMNLP.

[34]  Christopher Clark,et al.  Simple and Effective Multi-Paragraph Reading Comprehension , 2017, ACL.

[35]  Qi Wu,et al.  Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards , 2017, ArXiv.

[36]  Percy Liang,et al.  Know What You Don’t Know: Unanswerable Questions for SQuAD , 2018, ACL.

[37]  Hal Daumé,et al.  Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information , 2018, ACL.

[38]  Jun Xu,et al.  Reinforcing Coherence for Sequence to Sequence Model in Dialogue Generation , 2018, IJCAI.

[39]  Luke S. Zettlemoyer,et al.  AllenNLP: A Deep Semantic Natural Language Processing Platform , 2018, ArXiv.

[40]  Verena Rieser,et al.  Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity , 2018, EMNLP.

[41]  Christopher Potts,et al.  An Incremental Iterated Response Model of Pragmatics , 2018, ArXiv.

[42]  Percy Liang,et al.  Unifying Human and Statistical Evaluation for Natural Language Generation , 2019, NAACL.

[43]  Junyi Jessy Li,et al.  Domain Agnostic Real-Valued Specificity Prediction , 2018, AAAI.

[44]  Junyi Jessy Li,et al.  Linguistically-Informed Specificity and Semantic Plausibility for Dialogue Generation , 2019, NAACL.

[45]  Piji Li,et al.  Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling , 2019, ACL.

[46]  Danqi Chen,et al.  CoQA: A Conversational Question Answering Challenge , 2018, TACL.

[47]  Hal Daumé,et al.  Answer-based Adversarial Training for Generating Clarification Questions , 2019, NAACL.

[48]  Jason Weston,et al.  Wizard of Wikipedia: Knowledge-Powered Conversational agents , 2018, ICLR.

[49]  Jimmy J. Lin,et al.  Document Expansion by Query Prediction , 2019, ArXiv.

[50]  Tetsunori Kobayashi,et al.  Towards Answer-unaware Conversational Question Generation , 2019, MRQA@EMNLP.

[51]  Deng Cai,et al.  Reinforced Dynamic Reasoning for Conversational Question Generation , 2019, ACL.

[52]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[53]  Kilian Q. Weinberger,et al.  BERTScore: Evaluating Text Generation with BERT , 2019, ICLR.

[54]  Jacopo Staiano,et al.  Ask to Learn: A Study on Curiosity-driven Question Generation , 2019, COLING.

[55]  Dan Iter,et al.  Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models , 2020, ACL.