Neural Network Dialog System Papers

A list of papers about creating dialog systems using deep nets! Please feel free to add an issue or pull request for missing papers.

Bookmarks

• Task Bots
  • General
  • Multidomain & Domain Adaptation
  • User Simulator
  • Reinforcement Learning and Adversarial
• Chat Bots
  • General
  • Retrieval Methods
  • Rich Dialog Context
  • Diversity
  • Inteprebility

Task Bots

General

• Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks, Bing Liu, arXiv, 2016

• Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling, Bing Liu, arXiv, 2016

• A Network-based End-to-End Trainable Task-oriented Dialogue System Tsung-Hsien Wen et al, 2016

• Conditional Generation and Snapshot Learning in Neural Dialogue Systems Tsung-Hsien Wen et al, 2016

• Incorporating Unstructured Textual Knowledge Sources into Neural Dialogue Ryan Lowe et al., 2016

• End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning, Jason D. Williams et al., 2016

• End-to-End Reinforcement Learning of Dialogue Agents for Information Access Bhuwan Dhingra et al., 2016

• End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager Xuesong Yang et al., 2016

• Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning Jason D. Williams et al., 2017

• Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings He He et al., 2017

• Key-Value Retrieval Networks for Task-Oriented Dialogue M Eric et al., 2017

• Deal or No Deal? End-to-End Learning for Negotiation Dialogues Mike Lewis et al., 2017

• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability Tiancheng Zhao et al., 2017

• An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog Liu Bing et al., 2017

• End-to-End Recurrent Entity Network for Entity-Value Independent Goal-Oriented Dialog Learning CS Wu et al 2017 )

• Toward Continual Learning for Conversational Agents S Lee 2017

• Building a Conversational Agent Overnight with Dialogue Self-Play Pararth Shah et al 2018

• Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architecture Wenqiang Lei et al 2018

• Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems Andrea Madotto et al 2018

Multidomain & Domain Adaptation

• Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning Paweł et al., 2017

• Cross-domain Dialogue Policy Transfer via Simultaneous Speech-act and Slot Alignment Kaixiang Mo et al. 2018

• Zero-Shot Dialog Generation with Cross-Domain Latent Actions Tiancheng Zhao et al 2018

User Simulator

• Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System Jost Schatzmann 2007

• A User Simulator for Task-Completion Dialogues Xinjun Li et al., 2016

• A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems Layla El Asri 2016

• Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems Florian L. Kreyssig 2018

Reinforcement Learning and Adversarial

• Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning Tiancheng Zhao et al., 2016

• Deep Reinforcement Learning for Dialogue Generation Jiwei Li et al., arXiv, 2016

• Adversarial Learning for Neural Dialogue Generation Jiwei Li et al., 2017

• A deep reinforcement learning chatbot Serban et al 2017

• End-to-end Adversarial Learning for Generative Conversational Agents Ludwig, O. 2017.

• Strategic Dialogue Management via Deep Reinforcement Learning Heriberto Cuayáhuitl et al., 2015

• Generating Text with Deep Reinforcement Learning, Hongyu Guo, arXiv, 2015

• Deep Reinforcement Learning with a Natural Language Action Space, Ji He et al., arXiv, 2016.

• Language Understanding for Text-based Games using Deep Reinforcement Learning, Karthik Narasimhan arXiv, 2016

• Deep reinforcement learning for dialogue generation Jiwei Li et al., 2016

• End-to-end task-completion neural dialogue systems Xiujun Li et al., 2017

• Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning Paweł Budzianowski et al., 2017

• Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management Pei-Hao Su et al., 2017

• Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning Baolin Peng et al., 2017

• Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning Baolin Peng et al 2018

• Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog Jianping Zhang et al 2018

• Adversarial Learning of Task-Oriented Neural Dialog Models Bing Liu et al 2018.

Chat Bots

General

• A Neural Conversational Model Oriol Vinyals et al., arXiv 2015]

• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses∗ Alessandro Sordoni et al., arXiv 2015]

• Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation Iulian Vlad Serban et al., arXiv 2016s

• A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues Iulian Vlad Serban et al., 2016

• Online Sequence-to-Sequence Reinforcement Learning for Open-Domain Conversational Agents Nabiha Asghar et al., 2016

• Reinforcing Coherence for Sequence to Sequence Model in Dialogue Generation

• Multi-turn Dialogue Response Generation in an Adversarial Learning Framework - Combining GAN with MLE in the objective.

• Improving Variational Encoder-Decoders in Dialogue Generation X Shen et al 2018.

• MojiTalk: Generating Emotional Responses at Scale Xianda Zhou et al 2018

• Exemplar Encoder-Decoder for Neural Conversation Generation Gaurav Pandey et al 2018

• Coupled Context Modeling for Deep Chit-Chat: Towards Conversations between Human and Computer(http://www.ruiyan.me/pubs/KDD2018Yan.pdf) Rui Yan et al KDD 2018.

• Variational Autoregressive Decoder for Neural Response Generation Jiachen Du et al 2018.

Retrieval Methods

• Multi-view Response Selection for Human-Computer Conversation Xiangyang Zhou et al 2016

• Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots Yu Wu 2017

• Modeling multi-turn conversation with deep utterance aggregation Zhuosheng Zhang et al 2018

• Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network Xiangyang Zhang et al 2018.

Rich Dialog Context

• A Persona-Based Neural Conversation Model Jiwei Li et al, arXiv, 2016

• Conversational Contextual Cues: The Case of Personalization and History for Response Ranking Rami Al-Rfou et al., 2016

• Augmenting End-to-End Dialog Systems with Commonsense Knowledge Tom Young et al., 2017

• Topic Compositional Neural Language Model W Wang et al 2017

• Personalizing Dialogue Agents: I have a dog, do you have pets too? Zhang, Saizheng, et al., 2018

Some of the models are evaluated at CNN/Daily Mail and Children’s Book Test (CBT) corpora.

• Teaching Machines to Read and Comprehend, Karl Moritz Hermann et al., arXiv, 2015.
  • Deep LSTM/Attentive Reader/Impatient Reader

• Text Understanding with the Attention Sum Reader Network, Rudolf Kadlec et al., arXiv, 2016.

• The Goldlocks Principle: Reading Children’s Books With Explicit Memory Representations, Felix Hill., arXiv, 2016.
  • Memory Network

• End-To-End Memory Networks, Sainbayar Sukhbaatar et al., arXiv, 2015.

• Dynamic Entity Representation with Max-pooling Improves Machine Reading, Sosuke Kobayashi et al., arXiv, 2016.

• Gated-Attention Readers for Text Comprehension, Bhuwan Dhingra et al., arXiv, 2016.

• Iterative Alternating Neural Attention for Machine Reading, Alessandro Sordoni et al., arXiv, 2016.

• A Neural Network Approach to Context-Senstive Generation of Conversational Responses, Alessandro Sordoni et al, 2015

• Attention-over-Attention Neural Networks for Reading Comprehension Yiming Cui et al., arXiv 2016

• Hierarchical Recurrent Attention Network for Response Generation Chen Xing et al., 2017

• How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models Zhiliang Tian et al., 2017

• Chat More: Deepening and Widening the Chatting Topic via A Deep Model Wenjie Wang et al., 2018

Diversity

• A Diversity-Promoting Objective Function for Neural Conversation Models Jiwei Li et al. 2016

• A Simple, Fast Diverse Decoding Algorithm for Neural Generation Jiwei Li et al., 2016

• Data Distillation for Controlling Specificity in Dialogue Generation Jiwei Li et al., 2017

• Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models Louis Shao et al., 2017

• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders Tiancheng Zhao et al., 2017

• Latent variable dialogue models and their diversity Cao, Kris et al 2017

• DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder Xiaodong Gu et al 2018

• Towards a Neural Conversation Model with Diversity Net Using Determinantal Point Processes Yiping Song et al 2018

Inteprebility

• Latent intention dialogue models Tsung-Hsien Wen et al., 2017

• Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation Tiancheng Zhao et al., 2018

• Learning to Control the Specificity in Neural Response Generation Ruqing Zhang et al 2018.