PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation

Endowing a chatbot with a personality is essential to deliver more realistic conversations. Various persona-based dialogue models have been proposed to generate personalized and diverse responses by utilizing predefined persona information. However, generating personalized responses is still a challenging task since the leverage of predefined persona information is often insufficient. To alleviate this problem, we propose a novel Persona Enhanced Dual Alternating Learning Network (PEDNet) aiming at producing more personalized responses in various opendomain conversation scenarios. PEDNet consists of a Context-Dominated Network (CDNet) and a Persona-Dominated Network (PDNet), which are built upon a common encoder-decoder backbone. CDNet learns to select a proper persona as well as ensure the contextual relevance of the predicted response, while PDNet learns to enhance the utilization of persona information when generating the response by weakening the disturbance of specific content in the conversation context. CDNet and PDNet are trained alternately using a multi-task training approach to equip PEDNet with the both capabilities they have learned. Both automatic and human evaluations on a newly released dialogue dataset Persona-chat demonstrate that our method could deliver more personalized responses than baseline methods.

[1]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

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

[3]  Xiaoyu Wang,et al.  Exploring Personalized Neural Conversational Models , 2017, IJCAI.

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

[5]  Jason Weston,et al.  Personalizing Dialogue Agents: I have a dog, do you have pets too? , 2018, ACL.

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

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

[8]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

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

[10]  Ting Liu,et al.  Neural personalized response generation as domain adaptation , 2017, World Wide Web.

[11]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

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

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

[14]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[15]  Rui Yan,et al.  Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation , 2016, COLING.

[16]  Jason Weston,et al.  Wizard of Wikipedia: Knowledge-Powered Conversational agents , 2018, ICLR.

[17]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[18]  Rongzhong Lian,et al.  Learning to Select Knowledge for Response Generation in Dialog Systems , 2019, IJCAI.

[19]  Xiaoyan Zhu,et al.  Assigning Personality/Profile to a Chatting Machine for Coherent Conversation Generation , 2018, IJCAI.

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

[21]  Haoyu Song,et al.  Exploiting Persona Information for Diverse Generation of Conversational Responses , 2019, IJCAI.

[22]  Dilek Z. Hakkani-Tür,et al.  DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks , 2019, SIGdial.

[23]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.