https://github.com/snakeztc/NeuralDialogPapers

Summary of deep learning models for dialog systems (Tiancheng Zhao LTI, CMU)
https://github.com/snakeztc/NeuralDialogPapers

chatbot deep-learning language neural-network reinforcement-learning

Last synced: about 1 month ago
JSON representation

Summary of deep learning models for dialog systems (Tiancheng Zhao LTI, CMU)

• Host: GitHub
• URL: https://github.com/snakeztc/NeuralDialogPapers
• Owner: snakeztc
• Created: 2016-09-05T16:55:53.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2020-07-08T03:00:17.000Z (over 4 years ago)
• Last Synced: 2024-08-03T12:15:45.307Z (4 months ago)
• Topics: chatbot, deep-learning, language, neural-network, reinforcement-learning
• Homepage: https://snakeztc.github.io/NeuralDialogPapers
• Size: 46.9 KB
• Stars: 651
• Watchers: 69
• Forks: 136
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# 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](#task-bots)

    * General

    * Multidomain & Domain Adaptation

    * User Simulator

    * Reinforcement Learning and Adversarial 

  * [Chat Bots](#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](http://arxiv.org/abs/1609.01462v1), Bing Liu, *arXiv*, 2016

* [Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling](http://arxiv.org/abs/1609.01454v1), Bing Liu, *arXiv*, 2016

* [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://arxiv.org/abs/1604.04562) Tsung-Hsien Wen et al, 2016

* [Conditional Generation and Snapshot Learning in Neural Dialogue Systems](https://arxiv.org/abs/1606.03352) Tsung-Hsien Wen et al, 2016

* [Incorporating Unstructured Textual Knowledge Sources into Neural Dialogue](http://media.wix.com/ugd/b6d786_137894b7b3a341a09ed0c0b45b46dbb6.pdf) Ryan Lowe et al., 2016

* [End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning](http://arxiv.org/pdf/1606.01269v1.pdf), Jason D. Williams et al., 2016

* [End-to-End Reinforcement Learning of Dialogue Agents for Information Access](http://arxiv.org/abs/1609.00777) Bhuwan Dhingra et al., 2016

* [End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager](https://arxiv.org/abs/1612.00913) Xuesong Yang et al., 2016

* [Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning](https://arxiv.org/abs/1702.03274) Jason D. Williams et al., 2017

* [Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings](https://arxiv.org/abs/1704.07130) He He et al., 2017

* [Key-Value Retrieval Networks for Task-Oriented Dialogue](https://arxiv.org/abs/1705.05414) M Eric et al., 2017

* [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://arxiv.org/abs/1706.05125) Mike Lewis et al., 2017

* [Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability](https://arxiv.org/abs/1706.08476) Tiancheng Zhao et al., 2017

* [An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog](https://arxiv.org/pdf/1708.05956.pdf) Liu Bing et al., 2017

* [End-to-End Recurrent Entity Network for Entity-Value Independent Goal-Oriented Dialog Learning](http://workshop.colips.org/dstc6/papers/track1_paper02_wu.pdf) CS Wu et al 2017

) 

* [Toward Continual Learning for Conversational Agents](https://arxiv.org/pdf/1712.09943.pdf) S Lee 2017

* [Building a Conversational Agent Overnight with Dialogue Self-Play](https://arxiv.org/abs/1801.04871) Pararth Shah et al 2018

* [Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architecture](https://www.comp.nus.edu.sg/~xiangnan/papers/acl18-sequicity.pdf) Wenqiang Lei et al 2018

* [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://arxiv.org/abs/1804.08217) Andrea Madotto et al 2018

### Multidomain & Domain Adaptation

* [Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning](https://arxiv.org/pdf/1706.06210.pdf) Paweł et al., 2017

* [Cross-domain Dialogue Policy Transfer via Simultaneous Speech-act and Slot Alignment](https://arxiv.org/abs/1804.07691) Kaixiang Mo et al. 2018

* [Zero-Shot Dialog Generation with Cross-Domain Latent Actions](https://arxiv.org/abs/1805.04803) Tiancheng Zhao et al 2018

### User Simulator

* [Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System](http://mi.eng.cam.ac.uk/~sjy/papers/stwy07.pdf) Jost Schatzmann 2007

* [A User Simulator for Task-Completion Dialogues](https://arxiv.org/abs/1612.05688) Xinjun Li et al., 2016

* [A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems](https://arxiv.org/pdf/1607.00070.pdf) Layla El Asri 2016

* [Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems](https://arxiv.org/pdf/1805.06966.pdf) Florian L. Kreyssig 2018

### Reinforcement Learning and Adversarial 

* [Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning](https://arxiv.org/pdf/1606.02560v1.pdf) Tiancheng Zhao et al., 2016

* [Deep Reinforcement Learning for Dialogue Generation](https://arxiv.org/abs/1606.01541) Jiwei Li et al., *arXiv*, 2016

* [Adversarial Learning for Neural Dialogue Generation](https://arxiv.org/abs/1701.06547) Jiwei Li et al., 2017

* [A deep reinforcement learning chatbot](https://arxiv.org/abs/1709.02349) Serban et al 2017

* [End-to-end Adversarial Learning for Generative Conversational Agents](https://arxiv.org/abs/1711.10122) Ludwig, O. 2017. 

* [Strategic Dialogue Management via Deep Reinforcement Learning](https://arxiv.org/abs/1511.08099) Heriberto Cuayáhuitl et al., 2015

* [Generating Text with Deep Reinforcement Learning](http://arxiv.org/abs/1510.09202), Hongyu Guo, *arXiv*, 2015

* [Deep Reinforcement Learning with a Natural Language Action Space](http://arxiv.org/abs/1511.04636v5), Ji He et al., *arXiv*, 2016.

* [Language Understanding for Text-based Games using Deep Reinforcement Learning](https://arxiv.org/abs/1506.08941), Karthik Narasimhan *arXiv*, 2016

* [Deep reinforcement learning for dialogue generation](https://arxiv.org/abs/1606.01541) Jiwei Li et al., 2016

* [End-to-end task-completion neural dialogue systems](https://arxiv.org/abs/1703.01008) Xiujun Li et al., 2017

* [Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning](https://arxiv.org/abs/1706.06210) Paweł Budzianowski et al., 2017

* [Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management](https://arxiv.org/abs/1707.00130) Pei-Hao Su et al., 2017

* [Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning](https://arxiv.org/abs/1704.03084) Baolin Peng et al., 2017

* [Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning](https://arxiv.org/abs/1801.06176) Baolin Peng et al 2018

* [Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog](https://arxiv.org/abs/1805.03257) Jianping Zhang et al 2018

* [Adversarial Learning of Task-Oriented Neural Dialog Models](https://arxiv.org/abs/1805.11762) Bing Liu et al 2018.

## Chat Bots

### General

* [A Neural Conversational Model](http://arxiv.org/abs/1506.05869) Oriol Vinyals et al., *arXiv* 2015]

* [A Neural Network Approach to Context-Sensitive Generation of Conversational Responses∗](https://arxiv.org/pdf/1506.06714v1.pdf) 

Alessandro Sordoni et al., *arXiv* 2015]

* [Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation](https://arxiv.org/pdf/1606.00776v2.pdf) Iulian Vlad Serban et al., *arXiv* 2016s

* [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://arxiv.org/abs/1605.06069) Iulian Vlad Serban et al., 2016

* [Online Sequence-to-Sequence Reinforcement Learning for Open-Domain Conversational Agents](https://arxiv.org/abs/1612.03929) Nabiha Asghar et al., 2016

* [Reinforcing Coherence for Sequence to Sequence Model in Dialogue Generation](http://www.bigdatalab.ac.cn/~junxu/publications/IJCAI2018-DialogueGen.pdf)

* [Multi-turn Dialogue Response Generation in an Adversarial Learning Framework](https://arxiv.org/abs/1805.11752) - Combining GAN with MLE in the objective.

* [Improving Variational Encoder-Decoders in Dialogue Generation](https://arxiv.org/abs/1802.02032) X Shen et al 2018.

* [MojiTalk: Generating Emotional Responses at Scale](https://arxiv.org/abs/1711.04090) Xianda Zhou et al 2018

* [Exemplar Encoder-Decoder for Neural Conversation Generation](http://aclweb.org/anthology/P18-1123) 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](http://aclweb.org/anthology/D18-1354) Jiachen Du et al 2018.

### Retrieval Methods

* [Multi-view Response Selection for Human-Computer Conversation](http://www.aclweb.org/anthology/D16-1036) Xiangyang Zhou et al 2016

* [Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots](https://arxiv.org/abs/1612.01627) Yu Wu 2017

* [Modeling multi-turn conversation with deep utterance aggregation](https://arxiv.org/abs/1806.09102) Zhuosheng Zhang et al 2018

* [Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network](http://www.aclweb.org/anthology/P18-1103) Xiangyang Zhang et al 2018.

### Rich Dialog Context

* [A Persona-Based Neural Conversation Model](https://arxiv.org/abs/1603.06155) Jiwei Li et al, *arXiv*, 2016

* [Conversational Contextual Cues: The Case of Personalization and History for Response Ranking](http://arxiv.org/pdf/1606.00372v1.pdf) Rami Al-Rfou et al., 2016

* [Augmenting End-to-End Dialog Systems with Commonsense Knowledge](https://arxiv.org/abs/1709.05453) Tom Young et al., 2017

* [Topic Compositional Neural Language Model](https://arxiv.org/abs/1712.09783) W Wang et al 2017

* [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://arxiv.org/abs/1801.07243) 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](https://arxiv.org/abs/1506.03340), Karl Moritz Hermann et al., *arXiv*, 2015.

  * Deep LSTM/Attentive Reader/Impatient Reader

* [Text Understanding with the Attention Sum Reader Network](https://arxiv.org/abs/1603.01547), Rudolf Kadlec et al., *arXiv*, 2016.

* [The Goldlocks Principle: Reading Children's Books With Explicit Memory Representations](https://arxiv.org/abs/1511.02301), Felix Hill., *arXiv*, 2016.

  * Memory Network

* [End-To-End Memory Networks](http://arxiv.org/abs/1503.08895v5), Sainbayar Sukhbaatar et al., *arXiv*, 2015.

* [Dynamic Entity Representation with Max-pooling Improves Machine Reading](http://www.cl.ecei.tohoku.ac.jp/publications/2016/kobayashi-dynamic-entity-naacl2016.pdf), Sosuke Kobayashi et al., *arXiv*, 2016.

* [Gated-Attention Readers for Text Comprehension](https://arxiv.org/abs/1606.01549), Bhuwan Dhingra et al., *arXiv*, 2016.

* [Iterative Alternating Neural Attention for Machine Reading](http://arxiv.org/abs/1606.02245v3), Alessandro Sordoni et al., *arXiv*, 2016.

* [A Neural Network Approach to Context-Senstive Generation of Conversational Responses](https://michaelauli.github.io/papers/chitchat.pdf), Alessandro Sordoni et al, 2015

* [Attention-over-Attention Neural Networks for Reading Comprehension](https://arxiv.org/abs/1607.04423) Yiming Cui et al., *arXiv* 2016

* [Hierarchical Recurrent Attention Network for Response Generation](https://arxiv.org/pdf/1701.07149.pdf) Chen Xing et al., 2017

* [How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models](http://www.aclweb.org/anthology/P17-2036) Zhiliang Tian et al., 2017

* [Chat More: Deepening and Widening the Chatting Topic via A

Deep Model](http://coai.cs.tsinghua.edu.cn/hml/media/files/2018SIGIR_Wangwenjie.pdf) Wenjie Wang et al., 2018

### Diversity

* [A Diversity-Promoting Objective Function for Neural Conversation Models](http://www.aclweb.org/anthology/N16-1014) Jiwei Li et al. 2016

* [A Simple, Fast Diverse Decoding Algorithm for Neural Generation](https://arxiv.org/abs/1611.08562) Jiwei Li et al., 2016

* [Data Distillation for Controlling Specificity in Dialogue Generation](https://arxiv.org/abs/1702.06703) Jiwei Li et al., 2017

* [Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models](https://arxiv.org/abs/1701.03185) Louis Shao et al., 2017

* [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://arxiv.org/abs/1703.10960) Tiancheng Zhao et al., 2017

* [Latent variable dialogue models and their diversity](https://arxiv.org/abs/1702.05962) Cao, Kris et al 2017

* [DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder](https://arxiv.org/abs/1805.12352) Xiaodong Gu et al 2018

* [Towards a Neural Conversation Model with Diversity Net Using Determinantal Point Processes](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17115) Yiping Song et al 2018

### Inteprebility

* [Latent intention dialogue models](https://arxiv.org/abs/1705.10229) Tsung-Hsien Wen et al., 2017

* [Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation](https://arxiv.org/abs/1804.08069) Tiancheng Zhao et al., 2018

* [Learning to Control the Specificity in Neural Response Generation](http://aclweb.org/anthology/P18-1102) Ruqing Zhang et al 2018.