Learning to Ask Conversational Questions by Optimizing Levenshtein Distance

Conversational Question Simplification (CQS) aims to simplify self-contained questions into conversational ones by incorporating some conversational characteristics, e.g., anaphora and ellipsis. Existing maximum likelihood estimation based methods often get trapped in easily learned tokens as all tokens are treated equally during training. In this work, we introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimizes the minimum Levenshtein distance through explicit editing actions. RISE is able to pay attention to tokens that are related to conversational characteristics. To train RISE, we devise an Iterative Reinforce Training (IRT) algorithm with a Dynamic Programming based Sampling (DPS) process to improve exploration. Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods and generalizes well on unseen data.

[1]  Jimmy J. Lin,et al.  Query Reformulation using Query History for Passage Retrieval in Conversational Search , 2020, ArXiv.

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

[3]  Shashi Narayan,et al.  Leveraging Pre-trained Checkpoints for Sequence Generation Tasks , 2019, Transactions of the Association for Computational Linguistics.

[4]  Xiaojun Wan,et al.  Learning to Ask More: Semi-Autoregressive Sequential Question Generation under Dual-Graph Interaction , 2020, ACL.

[5]  Jamie Callan,et al.  Ranking Clarification Questions via Natural Language Inference , 2020, CIKM.

[6]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[7]  Minlie Huang,et al.  Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders , 2018, ACL.

[8]  Xu Chen,et al.  Towards Conversational Search and Recommendation: System Ask, User Respond , 2018, CIKM.

[9]  Paul N. Bennett,et al.  Leading Conversational Search by Suggesting Useful Questions , 2020, WWW.

[10]  Zhucheng Tu,et al.  Question Rewriting for Conversational Question Answering , 2020, ArXiv.

[11]  Hamed Zamani,et al.  Macaw: An Extensible Conversational Information Seeking Platform , 2019, SIGIR.

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

[13]  Alexander M. Rush,et al.  Sequence-to-Sequence Learning as Beam-Search Optimization , 2016, EMNLP.

[14]  Nan Duan,et al.  Asking Clarification Questions in Knowledge-Based Question Answering , 2019, EMNLP.

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

[16]  M. de Rijke,et al.  Query Resolution for Conversational Search with Limited Supervision , 2020, SIGIR.

[17]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[18]  M. de Rijke,et al.  Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation , 2019, AAAI.

[19]  Christopher C. Yang.  Search Engines Information Retrieval in Practice , 2010 .

[20]  M. de Rijke,et al.  Advances and Challenges in Conversational Recommender Systems: A Survey , 2021, AI Open.

[21]  Xiangnan He,et al.  Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems , 2020, WSDM.

[22]  M. de Rijke,et al.  Conversations with Search Engines , 2020, ArXiv.

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

[24]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[25]  C. Lawrence Zitnick,et al.  CIDEr: Consensus-based image description evaluation , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Jordan Boyd-Graber,et al.  Can You Unpack That? Learning to Rewrite Questions-in-Context , 2019, EMNLP.

[27]  Dong Yu,et al.  Semantic Role Labeling Guided Multi-turn Dialogue ReWriter , 2020, EMNLP.

[28]  W. Bruce Croft,et al.  Asking Clarifying Questions in Open-Domain Information-Seeking Conversations , 2019, SIGIR.

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

[30]  W. Bruce Croft,et al.  Search Engines - Information Retrieval in Practice , 2009 .

[31]  Yang Deng,et al.  Knowledge-aware Attentive Neural Network for Ranking Question Answer Pairs , 2018, SIGIR.

[32]  Hwee Tou Ng,et al.  Learning to Identify Follow-Up Questions in Conversational Question Answering , 2020, ACL.

[33]  Christopher D. Manning,et al.  Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations , 2020, FINDINGS.

[34]  Cheng Niu,et al.  Improving Multi-turn Dialogue Modelling with Utterance ReWriter , 2019, ACL.

[35]  Filip Radlinski,et al.  A Theoretical Framework for Conversational Search , 2017, CHIIR.

[36]  Ramón Fernández Astudillo,et al.  On the Importance of Diversity in Question Generation for QA , 2020, ACL.

[37]  Jimmy J. Lin,et al.  Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models , 2020, ArXiv.

[38]  Xu Sun,et al.  How to Ask Good Questions? Try to Leverage Paraphrases , 2020, ACL.

[39]  W. Bruce Croft,et al.  Open-Retrieval Conversational Question Answering , 2020, SIGIR.

[40]  Aliaksei Severyn,et al.  Encode, Tag, Realize: High-Precision Text Editing , 2019, EMNLP.

[41]  Paul N. Bennett,et al.  Generating Clarifying Questions for Information Retrieval , 2020, WWW.

[42]  Paul N. Bennett,et al.  Few-Shot Generative Conversational Query Rewriting , 2020, SIGIR.

[43]  Stephen G. Pulman.  Anaphora and ellipsis in artificial languages , 1995, Nat. Lang. Eng..

[44]  Chenyan Xiong,et al.  TREC CAsT 2019: The Conversational Assistance Track Overview , 2020, arXiv.org.

[45]  M. de Rijke,et al.  Wizard of Search Engine: Access to Information Through Conversations with Search Engines , 2021, SIGIR.

[46]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.