View Project


Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders


While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder at word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that captures the discourse-level diversity in the encoder. Our model uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders. We have further developed a novel variant that is integrated with linguistic prior knowledge for better performance. Finally, the training procedure is improved by introducing a bag-of-word loss. Our proposed models have been validated to generate significantly more diverse responses than baseline approaches and exhibit competence in discourse-level decision-making.


Login to edit or delete this resource.

Suggested Topics (up to Top 50)

Full Matches (full topic name in abstract)

Partial Matches (at least half of words topic name appear in abstract)

Suggested Resources

Uses abstract to search the content of resources available in Topics. Sorted by relevance.

# Title Author Topic Medium Score
1 How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation Chia-Wei Liu, Ryan Lowe, Iulian Serban, Mike Noseworthy, Laurent Ch... 999 paper 208.32
2 Deep Reinforcement Learning for Dialogue Generation Jiwei Li, Will Monroe, Alan Ritter, Dan Jurafsky, Michel Galley, Ji... 999 paper 203.25
3 A Latent Variable Recurrent Neural Network for Discourse-Driven Language Models Yangfeng Ji, Gholamreza Haffari, Jacob Eisenstein 999 paper 197.09
4 A Diversity-Promoting Objective Function for Neural Conversation Models Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan 999 paper 192.92
5 Representation Learning: A Review and New Perspectives Yoshua Bengio, Aaron Courville, Pascal Vincent 721 survey 190.27
6 Automatic Summarization Ani Nenkova and Kathleen McKeown 421 survey 185.61
7 Recent Advances in Document Summarization Jin-ge Yao, Xiaojun Wan, Jianguo Xiao 421 survey 185.03
8 GANs for Simulation, Representation and Inference Ari Heljakka tutorial 180.28
9 Speech and Language Processsing Dan Jurafsky and James Martin 863 tutorial 176.72
10 Deep Learning for Dialogue Systems Yun-Nung (Vivian) Chen, Asli Celikyilmaz, Dilek Hakkani-Tur 756 tutorial 173.85
11 Neural Network Methods for Natural Language Processing Yoav Goldberg 713 survey 171.64
12 Neural Text Generation: A Practical Guide Ziang Xie 431 survey 170.70
13 A Survey of Text Summarization Techniques Ani Nenkova, Kathleen McKeown 421 survey 170.09
14 PyTorch-GAN Jun-Yan Zhu, Richard Zhang, Deepak Pathak, Trevor Darrell, Alexei A... 731 library 168.92
15 WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia Daniel Hewlett, Alexandre Lacoste, Llion Jones, Illia Polosukhin, A... 999 paper 168.78
16 Learning Deep Architectures for AI Yoshua Bengio 712 survey 168.67
17 An Introduction to Deep Learning for Natural Language Processing Jianfeng Gao 711 tutorial 168.63
18 An Introduction to Neural Information Retrieval Bhaskar Mitra, Nick Craswell 232 survey 168.42
19 Reasoning about Pragmatics with Neural Listeners and Speakers Jacob Andreas, Dan Klein 999 paper 167.66
20 Deep Learning for NLP: An Overview of Recent Trends Elvis 711 resource 167.62
21 A tutorial survey of architectures, algorithms, and applications for deep learning Li Deng survey 167.33
22 Speech and Language Processing Daniel Jurafsky, James H. Martin 133 survey 166.76
23 Natural Language Understanding with Distributed Representation Kyunghyun Cho 721 survey 165.92
24 Brief Introduction to Machine Learning without Deep Learning Kyunghyun Cho 22 survey 165.92
25 Natural Language Processing Jacob Eisenstein 711 survey 165.23
26 Deep Learning for Conversational AI Pei-Hao Su, Nikola MrköiÊ, Iñigo Casanueva, Ivan VuliÊ 811 tutorial 164.08
27 A Persona-Based Neural Conversation Model Jiwei Li, Michel Galley, Chris Brockett, Georgios Spithourakis, Jia... 999 paper 164.01
28 Generative Adversarial Networks (GANs) Ian Goodfellow 341 tutorial 163.23
29 Generative Adversarial Networks (GANs) Ian Goodfellow 756 tutorial 163.23
30 Deep Learning Yoshua Bengio 711 tutorial 162.82
31 ICML+ACL’18: Structure Back in Play, Translation Wants More Context Andre Martins 956 resource 162.75
32 Deep Learning for Dialogue Systems Yun-Nung (Vivian) Chen, Asli Celikyilmaz, Dilek Hakkani-Tur 445 tutorial 162.65
33 The 7 NLP Techniques That Will Change How You Communicate in the Future (Part I) James Le 112 resource 162.64
34 Sentiment Analysis and Opinion Mining Bing Liu 381 survey 160.92
35 Opinion mining and sentiment analysis Bo Pang and Lillian Lee 381 survey 159.87
36 Advanced Dialog Systems Daniel Jurafsky, James H. Martin 445 survey 159.65
37 Conditional Generation and Snapshot Learning in Neural Dialogue Systems Tsung-Hsien Wen, Milica Gasic, Nikola Mrkši?, Lina M. Rojas Barahon... 999 paper 159.63
38 Artificial Intelligence and Games Georgios N. Yannakakis and Julian Togelius 825 survey 159.13
39 Neural Networks for Information Retrieval Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani,... tutorial 158.15
40 Natural Language Processing Jacob Eisenstein 711 survey 157.69
41 Deep Reinforcement Learning: An Overview Yuxi Li 857 resource 157.22
42 Summaries and notes on Deep Learning research papers Denny Britz 713 resource 157.08
43 Neural Information Retrieval: At the End of the Early Years Kezban Dilek Onal, Ye Zhang, Ismail Sengor Altingovde, Md Mustafizu... 713 resource 156.26
44 A Survey on Automatic Text Summarization Dipanjan Das, Andre F.T. Martins 411 survey 155.83
45 The problem with Neural Chatbots Ryan Lowe 756 tutorial 155.32
46 ICML 2018 Notes David Abel 999 survey 153.57
47 From Feature To Paradigm: Deep Learning In Machine Translation Marta R. Costa-juss? survey 153.33
48 From Feature to Paradigm: Deep Learning in Machine Translation Marta R. Costa-juss`a 451 survey 153.33
49 Neural Machine Translation and Sequence-to-sequence Models: A Tutorial Graham Neubig 999 paper 152.53
50 Language to Logical Form with Neural Attention Li Dong, Mirella Lapata 999 paper 151.63