Modelling Context Emotions using Multi-task Learning for Emotion Controlled Dialog Generation

A recent topic of research in natural language generation has been the development of automatic response generation modules that can automatically respond to a user’s utterance in an empathetic manner. Previous research has tackled this task using neural generative methods by augmenting emotion classes with the input sequences. However, the outputs by these models may be inconsistent. We employ multi-task learning to predict the emotion label and to generate a viable response for a given utterance using a common encoder with multiple decoders. Our proposed encoder-decoder model consists of a self-attention based encoder and a decoder with dot product attention mechanism to generate response with a specified emotion. We use the focal loss to handle imbalanced data distribution, and utilize the consistency loss to allow coherent decoding by the decoders. Human evaluation reveals that our model produces more emotionally pertinent responses. In addition, our model outperforms multiple strong baselines on automatic evaluation measures such as F1 and BLEU scores, thus resulting in more fluent and adequate responses.

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

[2]  Catherine Pelachaud,et al.  An empathic virtual dialog agent to improve human-machine interaction , 2008, AAMAS.

[3]  Chunyan Miao,et al.  An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss , 2018, AAAI.

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

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

[6]  Samy Bengio,et al.  Content preserving text generation with attribute controls , 2018, NeurIPS.

[7]  Alex Waibel,et al.  EMOTION-SENSITIVE HUMAN-COMPUTER INTERFACES , 2000 .

[8]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

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

[10]  Xiaodong Liu,et al.  Multi-Task Deep Neural Networks for Natural Language Understanding , 2019, ACL.

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

[12]  Pascale Fung,et al.  CAiRE: An End-to-End Empathetic Chatbot , 2019, AAAI.

[13]  Yoshimasa Tsuruoka,et al.  A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks , 2016, EMNLP.

[14]  Marcin Skowron,et al.  Affect Listeners: Acquisition of Affective States by Means of Conversational Systems , 2009, COST 2102 Training School.

[15]  Satoshi Nakamura,et al.  Eliciting Positive Emotion through Affect-Sensitive Dialogue Response Generation: A Neural Network Approach , 2018, AAAI.

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

[17]  Eric P. Xing,et al.  Toward Controlled Generation of Text , 2017, ICML.

[18]  Xuanjing Huang,et al.  Generating Responses with a Specific Emotion in Dialog , 2019, ACL.

[19]  Quoc V. Le,et al.  Multi-task Sequence to Sequence Learning , 2015, ICLR.

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

[21]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Ke Wang,et al.  SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks , 2018, IJCAI.

[23]  Qiang Yang,et al.  An Overview of Multi-task Learning , 2018 .

[24]  Ming-Wei Chang,et al.  A Knowledge-Grounded Neural Conversation Model , 2017, AAAI.

[25]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[26]  James Kennedy,et al.  Affect-Driven Dialog Generation , 2019, NAACL.

[27]  Mitsuru Ishizuka,et al.  THE EMPATHIC COMPANION: A CHARACTER-BASED INTERFACE THAT ADDRESSES USERS' AFFECTIVE STATES , 2005, Appl. Artif. Intell..

[28]  Toru Nishino,et al.  Keeping Consistency of Sentence Generation and Document Classification with Multi-Task Learning , 2019, EMNLP.

[29]  Zhaopeng Tu,et al.  EmpGAN: Multi-resolution Interactive Empathetic Dialogue Generation , 2019, ArXiv.

[30]  Joelle Pineau,et al.  Hierarchical Neural Network Generative Models for Movie Dialogues , 2015, ArXiv.

[31]  Pushpak Bhattacharyya,et al.  Courteously Yours: Inducing courteous behavior in Customer Care responses using Reinforced Pointer Generator Network , 2019, NAACL.

[32]  Y-Lan Boureau,et al.  Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset , 2018, ACL.

[33]  Mohit Bansal,et al.  Polite Dialogue Generation Without Parallel Data , 2018, TACL.

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

[35]  Jesse Hoey,et al.  Affective Neural Response Generation , 2017, ECIR.

[36]  Louis-Philippe Morency,et al.  Affect-LM: A Neural Language Model for Customizable Affective Text Generation , 2017, ACL.

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

[38]  J. Fleiss.  Measuring nominal scale agreement among many raters. , 1971 .