Neural Conversation Model Controllable by Given Dialogue Act Based on Adversarial Learning and Label-aware Objective

Building a controllable neural conversation model (NCM) is an important task. In this paper, we focus on controlling the responses of NCMs by using dialogue act labels of responses as conditions. We introduce an adversarial learning framework for the task of generating conditional responses with a new objective to a discriminator, which explicitly distinguishes sentences by using labels. This change strongly encourages the generation of label-conditioned sentences. We compared the proposed method with some existing methods for generating conditional responses. The experimental results show that our proposed method has higher controllability for dialogue acts even though it has higher or comparable naturalness to existing methods.

[1]  Lantao Yu,et al.  SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient , 2016, AAAI.

[2]  Dongyan Zhao,et al.  How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models , 2017, ACL.

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

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

[5]  Yang Zhao,et al.  A Conditional Variational Framework for Dialog Generation , 2017, ACL.

[6]  Sadao Kurohashi,et al.  Chat-Like Conversational System Based on Selection of Reply Generating Module with Reinforcement Learning , 2014, IWSDS.

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

[8]  Yiming Yang,et al.  An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation , 2019, ArXiv.

[9]  Cyril Goutte.  Automatic Evaluation of Machine Translation Quality , 2006 .

[10]  Quan Hung Tran,et al.  A Hierarchical Neural Model for Learning Sequences of Dialogue Acts , 2017, EACL.

[11]  Milica Gasic,et al.  The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management , 2010, Comput. Speech Lang..

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

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

[14]  Tatsuya Kawahara,et al.  Conversational system for information navigation based on POMDP with user focus tracking , 2015, Comput. Speech Lang..

[15]  M. de Rijke,et al.  Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning , 2018, AAAI.

[16]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

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

[18]  Ryuichiro Higashinaka,et al.  Controlling Listening-oriented Dialogue using Partially Observable Markov Decision Processes , 2010, COLING.

[19]  Hung-Yi Lee,et al.  Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation , 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[20]  Xiao Sun,et al.  Emotional Human Machine Conversation Generation Based on SeqGAN , 2018, 2018 First Asian Conference on Affective Computing and Intelligent Interaction (ACII Asia).

[21]  Alexander I. Rudnicky,et al.  Stochastic Language Generation for Spoken Dialogue Systems , 2000 .

[22]  Yu Zhang,et al.  Simple Recurrent Units for Highly Parallelizable Recurrence , 2017, EMNLP.

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

[24]  Augustus Odena,et al.  Semi-Supervised Learning with Generative Adversarial Networks , 2016, ArXiv.

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

[26]  Xiao Sun,et al.  Emotional Human-Machine Conversation Generation Based on Long Short-Term Memory , 2017, Cognitive Computation.

[27]  Yu Zhang,et al.  Training RNNs as Fast as CNNs , 2017, EMNLP 2018.

[28]  William Yang Wang,et al.  MojiTalk: Generating Emotional Responses at Scale , 2017, ACL.

[29]  David Vandyke,et al.  Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems , 2015, EMNLP.

[30]  Kôiti Hasida,et al.  ISO 24617-2: A semantically-based standard for dialogue annotation , 2012, LREC.

[31]  Alexander I. Rudnicky,et al.  Task-based dialog management using an agenda , 2000 .

[32]  Xiaoyan Zhu,et al.  Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory , 2017, AAAI.

[33]  Xiaoyu Shen,et al.  DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset , 2017, IJCNLP.

[34]  Osmar R. Zaïane,et al.  Automatic Dialogue Generation with Expressed Emotions , 2018, NAACL.

[35]  Verena Rieser,et al.  Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling , 2018, ArXiv.

[36]  Alan Ritter,et al.  Adversarial Learning for Neural Dialogue Generation , 2017, EMNLP.

[37]  Kristy Elizabeth Boyer,et al.  Dialogue Act Modeling in a Complex Task-Oriented Domain , 2010, SIGDIAL Conference.