A memory network based end-to-end personalized task-oriented dialogue generation

Abstract Building a personalized task-oriented dialogue system is an important but challenging task. Significant success has been achieved in the template selection responses. However, preparing a massive response template is time-consuming and human-labor intensive. In this paper, we propose an end-to-end framework based on memory networks for response generation in a personalized task-oriented dialogue system. Our model consists of three parts: a retrieval module, a memory encoder network and a memory decoder network. Retrieval module employs the user utterances and user attributes to collect relevant responses from other users. Memory encoder is trained with textual features to obtain dialogue representation. Memory decoder is composed of an RNN and a rule-memory network for response generation. Experiments on the benchmark dataset show that our model achieves better performance than strong baselines in personalized task-oriented dialogue generation.

[1]  Jason Weston,et al.  Key-Value Memory Networks for Directly Reading Documents , 2016, EMNLP.

[2]  Mona T. Diab,et al.  Multi-Domain Goal-Oriented Dialogues (MultiDoGO): Strategies toward Curating and Annotating Large Scale Dialogue Data , 2019, EMNLP.

[3]  Dongyan Zhao,et al.  An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems , 2018, IJCAI.

[4]  Gary Geunbae Lee,et al.  Acquisition and Use of Long-Term Memory for Personalized Dialog Systems , 2014, MA3HMI@INTERSPEECH.

[5]  Yann Dauphin,et al.  Convolutional Sequence to Sequence Learning , 2017, ICML.

[6]  Boi Faltings,et al.  Personalization in Goal-Oriented Dialog , 2017, ArXiv.

[7]  Xu Sun,et al.  Learning Personalized End-to-End Goal-Oriented Dialog , 2018, AAAI.

[8]  Peng Xu,et al.  Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables , 2019, EMNLP.

[9]  Richard Socher,et al.  Pointer Sentinel Mixture Models , 2016, ICLR.

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

[11]  Jason Weston,et al.  Retrieve and Refine: Improved Sequence Generation Models For Dialogue , 2018, SCAI@EMNLP.

[12]  Chenguang Zhu,et al.  Multi-task Learning for Natural Language Generation in Task-Oriented Dialogue , 2019, EMNLP.

[13]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[14]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[15]  Pat Langley,et al.  A Personalized System for Conversational Recommendations , 2011, J. Artif. Intell. Res..

[16]  Pascale Fung,et al.  Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems , 2018, ACL.

[17]  Zhoujun Li,et al.  Building Task-Oriented Dialogue Systems for Online Shopping , 2017, AAAI.

[18]  Christopher D. Manning,et al.  A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue , 2017, EACL.

[19]  Min Yang,et al.  Investigating Deep Reinforcement Learning Techniques in Personalized Dialogue Generation , 2018, SDM.

[20]  Yu Zhang,et al.  Personalizing a Dialogue System With Transfer Reinforcement Learning , 2016, AAAI.

[21]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

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

[23]  Jiliang Tang,et al.  A Survey on Dialogue Systems: Recent Advances and New Frontiers , 2017, SKDD.

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

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

[26]  David Konopnicki,et al.  Neural Response Generation for Customer Service based on Personality Traits , 2017, INLG.

[27]  Yu Zhang,et al.  Personalizing a Dialogue System with Transfer Learning , 2016, ArXiv.

[28]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[29]  Min Yang,et al.  Personalized response generation by Dual-learning based domain adaptation , 2018, Neural Networks.

[30]  Jianfeng Gao,et al.  Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models , 2017, IJCNLP.

[31]  Yunming Ye,et al.  Learning Personalized End-to-End Task-Oriented Dialogue Generation , 2019, NLPCC.

[32]  Matthew Henderson,et al.  Training Neural Response Selection for Task-Oriented Dialogue Systems , 2019, ACL.

[33]  Gary Geunbae Lee,et al.  Example-based chat-oriented dialogue system with personalized long-term memory , 2015, 2015 International Conference on Big Data and Smart Computing (BIGCOMP).

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

[35]  Richard Socher,et al.  Global-to-local Memory Pointer Networks for Task-Oriented Dialogue , 2019, ICLR.