Getting Your Conversation on Track: Estimation of Residual Life for Conversations

This paper presents a predictive study on the progress of conversations. Specifically, we estimate the residual life for conversations, which is defined as the count of new turns to occur in a conversation thread. While most previous work focus on coarse-grained estimation that classifies the number of coming turns into two categories, we study fine-grained categorization for varying lengths of residual life. To this end, we propose a hierarchical neural model that jointly explores indicative representations from the content in turns and the structure of conversations in an end-to-end manner. Extensive experiments on both human-human and human-machine conversations demonstrate the superiority of our proposed model and its potential helpfulness in chatbot response selection.

[1]  Denny Britz,et al.  Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models , 2017, EMNLP.

[2]  Shujian Huang,et al.  Dialogue State Tracking with Explicit Slot Connection Modeling , 2020, ACL.

[3]  E. Schegloff,et al.  A simplest systematics for the organization of turn-taking for conversation , 1974 .

[4]  Michael Gamon,et al.  Predicting Responses to Microblog Posts , 2012, NAACL.

[5]  Jon M. Kleinberg,et al.  Characterizing and curating conversation threads: expansion, focus, volume, re-entry , 2013, WSDM.

[6]  Qun Liu,et al.  HHMM-based Chinese Lexical Analyzer ICTCLAS , 2003, SIGHAN.

[7]  Alexander I. Rudnicky,et al.  A Wizard-of-Oz Study on A Non-Task-Oriented Dialog Systems That Reacts to User Engagement , 2016, SIGDIAL Conference.

[8]  Anne Tissen,et al.  A case-based architecture for a dialogue manager for information-seeking processes , 1991, SIGIR '91.

[9]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[10]  Gleb Gusev,et al.  Prediction of retweet cascade size over time , 2012, CIKM.

[11]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[12]  Ruihong Huang,et al.  Improving Dialogue State Tracking by Discerning the Relevant Context , 2019, NAACL-HLT.

[13]  Ed H. Chi,et al.  Want to be Retweeted? Large Scale Analytics on Factors Impacting Retweet in Twitter Network , 2010, 2010 IEEE Second International Conference on Social Computing.

[14]  Jia Wang,et al.  Topological Recurrent Neural Network for Diffusion Prediction , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[15]  Mari Ostendorf,et al.  A Dynamic Speaker Model for Conversational Interactions , 2019, NAACL.

[16]  Cheng Li,et al.  DeepCas: An End-to-end Predictor of Information Cascades , 2016, WWW.

[17]  Xiaoming Zhang,et al.  Hierarchy Response Learning for Neural Conversation Generation , 2019, EMNLP/IJCNLP.

[18]  Satoshi Nakamura,et al.  Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding , 2019, Proceedings of the First Workshop on NLP for Conversational AI.

[19]  Wei-Ying Ma,et al.  Topic Aware Neural Response Generation , 2016, AAAI.

[20]  Matthew Rowe,et al.  Predicting Discussions on the Social Semantic Web , 2011, ESWC.

[21]  Fatih Uzdilli,et al.  A Twitter Corpus and Benchmark Resources for German Sentiment Analysis , 2017, SocialNLP@EACL.

[22]  John Canny,et al.  What’s The Latest? A Question-driven News Chatbot , 2020, ACL.

[23]  Xuanjing Huang,et al.  Keyphrase Extraction Using Deep Recurrent Neural Networks on Twitter , 2016, EMNLP.

[24]  Yan Liu,et al.  Towards Twitter context summarization with user influence models , 2013, WSDM.

[25]  Brian D. Davison,et al.  Predicting popular messages in Twitter , 2011, WWW.

[26]  Jie Zhou,et al.  A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking , 2020, ACL.

[27]  Tatsuya Kawahara,et al.  Detection of social signals for recognizing engagement in human-robot interaction , 2017, ArXiv.

[28]  Hao Wang,et al.  A Dataset for Research on Short-Text Conversations , 2013, EMNLP.

[29]  Wei Gao,et al.  Topic Extraction from Microblog Posts Using Conversation Structures , 2016, ACL.

[30]  Zhou Yu,et al.  Incremental Coordination: Attention-Centric Speech Production in a Physically Situated Conversational Agent , 2015, SIGDIAL Conference.

[31]  Cristian Danescu-Niculescu-Mizil,et al.  Chameleons in Imagined Conversations: A New Approach to Understanding Coordination of Linguistic Style in Dialogs , 2011, CMCL@ACL.

[32]  Matthew Rowe,et al.  Anticipating Discussion Activity on Community Forums , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.

[33]  David Suendermann-Oeft,et al.  An Open-Source Dialog System with Real-Time Engagement Tracking for Job Interview Training Applications , 2017, IWSDS.

[34]  Bill Byrne,et al.  Semi-supervised Bootstrapping of Dialogue State Trackers for Task Oriented Modelling , 2019, EMNLP/IJCNLP.

[36]  Cheng Li,et al.  Find the Conversation Killers: A Predictive Study of Thread-ending Posts , 2017, WWW.

[37]  Douglas A. Reynolds,et al.  Text independent speaker identification using automatic acoustic segmentation , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[38]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[39]  Jason Weston,et al.  Learning from Dialogue after Deployment: Feed Yourself, Chatbot! , 2019, ACL.

[40]  Yang Feng,et al.  Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variables , 2019, ACL.

[41]  Daniel Jurafsky,et al.  A Hierarchical Neural Autoencoder for Paragraphs and Documents , 2015, ACL.