MOSS: End-to-End Dialog System Framework with Modular Supervision

A major bottleneck in training end-to-end task-oriented dialog system is the lack of data. To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an encoder-decoder training framework that could incorporate supervision from various intermediate dialog system modules including natural language understanding, dialog state tracking, dialog policy learning, and natural language generation. With only 60% of the training data, MOSS-all (i.e., MOSS with supervision from all four dialog modules) outperforms state-of-the-art models on CamRest676. Moreover, introducing modular supervision has even bigger benefits when the dialog task has a more complex dialog state and action space. With only 40% of the training data, MOSS-all outperforms the state-of-the-art model on a complex laptop network troubleshooting dataset, LaptopNetwork, that we introduced. LaptopNetwork consists of conversations between real customers and customer service agents in Chinese. Moreover, MOSS framework can accommodate dialogs that have supervision from different dialog modules at both the framework level and model level. Therefore, MOSS is extremely flexible to update in a real-world deployment.

[1]  Yann Dauphin,et al.  Deal or No Deal? End-to-End Learning of Negotiation Dialogues , 2017, EMNLP.

[2]  Joelle Pineau,et al.  Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus , 2017, Dialogue Discourse.

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

[4]  Zhou Yu,et al.  Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good , 2019, ACL.

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

[6]  Derek Chen,et al.  Decoupling Strategy and Generation in Negotiation Dialogues , 2018, EMNLP.

[7]  Stefan Ultes,et al.  MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling , 2018, EMNLP.

[8]  Dilek Z. Hakkani-Tür,et al.  Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems , 2018, NAACL.

[9]  Min-Yen Kan,et al.  Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures , 2018, ACL.

[10]  David Vandyke,et al.  Conditional Generation and Snapshot Learning in Neural Dialogue Systems , 2016, EMNLP.

[11]  Joelle Pineau,et al.  A Survey of Available Corpora for Building Data-Driven Dialogue Systems , 2015, Dialogue Discourse.

[12]  Christopher D. Manning,et al.  Key-Value Retrieval Networks for Task-Oriented Dialogue , 2017, SIGDIAL Conference.

[13]  Bing Liu,et al.  Incorporating the Structure of the Belief State in End-to-End Task-Oriented Dialogue Systems , 2018 .

[14]  Steve J. Young,et al.  Partially observable Markov decision processes for spoken dialog systems , 2007, Comput. Speech Lang..

[15]  Sungjin Lee.  Extrinsic Evaluation of Dialog State Tracking and Predictive Metrics for Dialog Policy Optimization , 2014, SIGDIAL Conference.

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

[17]  Jianfeng Gao,et al.  End-to-End Task-Completion Neural Dialogue Systems , 2017, IJCNLP.

[18]  Tsung-Hsien Wen,et al.  Latent Intention Dialogue Models , 2017, ICML.

[19]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

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

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