NVSRN: A Neural Variational Scaling Reasoning Network for Initiative Response Generation

Open-domain multi-turn dialogue systems are booming in human-machine interactions, which encourage to chat actively and freely in an intelligent natural way. Previous generative conversational models usually employ a single and deterministic encoder-decoder framework to model the semantic consistency between the context and corresponding response. However, they neglect the various dialog patterns (we denote the regularity of topic shifting as dialog pattern) in the conversations, leading to uninformative, non-initiative yet plausible responses. Although the existing variational methods have improved the response diversity to some extent by introducing a global variability into the generative process, they fail to simulate the transfer between topics with directional information due to the weak interpretability of the Gaussian-distributed latent variables. In this paper, we propose a novel Neural Variational Scaling Reasoning Network (NVSRN) for initiative response generation. To this end, our approach has two core ingredients: neural dialog pattern reasoner (reasoner) and topic scaling mechanism. Specifically, inspired by the advantage of von Mises-Fisher (vMF) distribution modeling the directional data (e.g., the topic transfer state), we employ it as the latent space of the reasoner to explore the regularity of topic shifting, which is then used to reason the topic of response. Based on this, a topic scaling mechanism is designed to control the transfer degree of topic in the response generator. The experimental results on two large dialog datasets demonstrate that the proposed model outperforms state-of-the-art baselines. The human evaluation shows the proposed model can produce more informative and initiative responses actively.

[1]  K. Mardia Statistics of Directional Data , 1972 .

[2]  Jacob Cohen,et al.  The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of Reliability , 1973 .

[3]  Lidong Bing,et al.  Recurrent Attention Network on Memory for Aspect Sentiment Analysis , 2017, EMNLP.

[4]  Nematollah Batmanghelich,et al.  Nonparametric Spherical Topic Modeling with Word Embeddings , 2016, ACL.

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

[6]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

[7]  Regina Barzilay,et al.  Style Transfer from Non-Parallel Text by Cross-Alignment , 2017, NIPS.

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

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

[10]  Alan Ritter,et al.  Data-Driven Response Generation in Social Media , 2011, EMNLP.

[11]  A. Wood Simulation of the von mises fisher distribution , 1994 .

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

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

[14]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[15]  Joelle Pineau,et al.  A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues , 2016, AAAI.

[16]  Jianfeng Gao,et al.  deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets , 2015, ACL.

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

[18]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

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

[20]  Haizhou Li,et al.  IRIS: a Chat-oriented Dialogue System based on the Vector Space Model , 2012, ACL.

[21]  Jianfeng Gao,et al.  A Diversity-Promoting Objective Function for Neural Conversation Models , 2015, NAACL.

[22]  Maxine Eskénazi,et al.  Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders , 2017, ACL.

[23]  Mike Lewis,et al.  Hierarchical Text Generation and Planning for Strategic Dialogue , 2017, ICML.

[24]  Percy Liang,et al.  Generating Sentences by Editing Prototypes , 2017, TACL.

[25]  Rui Yan,et al.  Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System , 2016, SIGIR.

[26]  Nebojsa Jojic,et al.  Steering Output Style and Topic in Neural Response Generation , 2017, EMNLP.

[27]  Zhaochun Ren,et al.  Hierarchical Variational Memory Network for Dialogue Generation , 2018, WWW.

[28]  Bo Chen,et al.  Mechanism-Aware Neural Machine for Dialogue Response Generation , 2017, AAAI.

[29]  Zhoujun Li,et al.  Sequential Match Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots , 2016, ArXiv.

[30]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[31]  Alexander M. Rush,et al.  Adversarially Regularized Autoencoders , 2017, ICML.

[32]  Dongyan Zhao,et al.  Joint Learning of Response Ranking and Next Utterance Suggestion in Human-Computer Conversation System , 2017, SIGIR.

[33]  Jiacheng Xu,et al.  Spherical Latent Spaces for Stable Variational Autoencoders , 2018, EMNLP.

[34]  Fumin Shen,et al.  Chat More: Deepening and Widening the Chatting Topic via A Deep Model , 2018, SIGIR.

[35]  Jianfeng Gao,et al.  A Neural Network Approach to Context-Sensitive Generation of Conversational Responses , 2015, NAACL.

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

[37]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[38]  Bo Fu,et al.  Integrating Topic Modeling with Word Embeddings by Mixtures of vMFs , 2016, COLING.

[39]  Xueqi Cheng,et al.  Learning to Control the Specificity in Neural Response Generation , 2018, ACL.

[40]  Zi-Yi Dou,et al.  Capturing User and Product Information for Document Level Sentiment Analysis with Deep Memory Network , 2017, EMNLP.

[41]  Hang Li,et al.  Neural Responding Machine for Short-Text Conversation , 2015, ACL.

[42]  Jianfeng Gao,et al.  A Persona-Based Neural Conversation Model , 2016, ACL.

[43]  Yang Feng,et al.  Knowledge Diffusion for Neural Dialogue Generation , 2018, ACL.