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.



Suggested Topics

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 Recent Advances in Document Summarization Jin-ge Yao, Xiaojun Wan, Jianguo Xiao 421 survey 211.92
2 Neural Information Retrieval: At the End of the Early Years Kezban Dilek Onal, Ye Zhang, Ismail Sengor Altingovde, Md Mustafizur Rahman, Pinar Karagoz, Alex Braylan, Brandon Dang, Heng-Lu Chang, Henna Kim, Quinten McNamara, Aaron Angert, Edward Banner, Vivek K 713 resource 196.74
3 PyTorch-GAN Jun-Yan Zhu, Richard Zhang, Deepak Pathak, Trevor Darrell, Alexei A. Efros, Oliver Wang, Eli Shechtman 731 library 182.85
4 The 7 NLP Techniques That Will Change How You Communicate in the Future (Part I) James Le 112 resource 172.68
5 ICML+ACL’18: Structure Back in Play, Translation Wants More Context Andre Martins 956 resource 170.25
6 Deep Learning for NLP: An Overview of Recent Trends Elvis 711 resource 168.15
7 Codra: A Novel Discriminative Framework for Rhetorical Analysis Shafiq Joty, Giuseppe Carenini, Raymond T. Ng 999 paper 167.21
9 NLP’s generalization problem, and how researchers are tackling it Ana Marasovic 711 resource 158.57
10 Summaries and notes on Deep Learning research papers Denny Britz 713 resource 157.31
11 A survey of transfer learning Karl Weiss, Taghi M. Khoshgoftaar and DingDing Wang 978 resource 151.87
12 A Comparative Analysis of ChatBots APIs Author Unknown 921 resource 151.01
13 Discriminative Syntax-based Word Ordering for Text Generation Yue Zhang, Stephen Clark 999 paper 150.69
14 The 7 NLP Techniques That Will Change How You Communicate in the Future (Part II) James Le 133 resource 150.50
15 Deep Learning Summer School Invited Speakers with slides CIFAR 713 resource 148.03
16 Chatsbots with Machine Learning: Building Neural Conversational Agents Dmitry Persiyanov 999 resource 146.95
17 Using Artificial Intelligence to Augment Human Intelligence Shan Carter, Michael Nielsen 811 resource 146.34
18 DEEP LEARNING FOR CHATBOTS, PART 1 - INTRODUCTION Denny Britz 445 tutorial 144.56
19 The Current Best of Universal Word Embeddings and Sentence Embeddings Thomas Wolf 721 resource 143.05
20 Neural Text Embeddings for IR Bhaskar Mitra, Nick Craswell 721 tutorial 142.97
21 Tombones Computer Vision Blog Tomasz Malisiewicz 958 resource 142.74
22 Diversity and network coherence as indicators of interdisciplinarity: case studies in bionanoscience Ismael Rafols, Martin Meyer 999 paper 142.35
23 Similarity-driven Semantic Role Induction via Graph Partitioning Joel Lang, Mirella Lapata 999 paper 142.06
24 Transfer Learning - Machine Learnings Next Frontier Sebastian Ruder 978 tutorial 139.07
25 Deep Learning for NLP Best Practices Sebastian Ruder 713 tutorial 138.50
26 A Gentle Introduction to Neural Networks for Machine Learning James Le 711 resource 137.21
27 A survey of cross-lingual embedding models Sebastian Ruder 721 tutorial 136.68
28 Building a FAQ Chatbot in Python – The Future of Information Searching Yogesh Kulkarni 232 resource 133.95
29 Highlights of EMNLP 2017: Exciting Datasets, Return of the Clusters, and More! Sebastian Ruder 641 resource 133.70
30 NLP's ImageNet moment has arrived Sebastian Ruder 862 resource 133.55
31 End-to-end speech Anthony Ndirango 863 resource 133.11
32 The 10 Neural Network Architectures Machine Learning Researchers Need To Learn James Le 641 resource 132.91
33 Deep Learning for NLP, advancements and trends in 2017 Javier 711 resource 132.55
34 Neural Machine Translation (seq2seq) Tutorial Thang Luong, Eugene Brevdo, Rui Zhao 753 tutorial 132.43
35 What I learned from Deep Learning Summer School 2016 Hamid Palangi 107 tutorial 131.89
36 ACL 2017 Report Yuta Kikuchi, Sosuke Kobayashi 711 resource 131.89
37 Building Autoencoders in Keras Francois Chollet 731 tutorial 131.67
38 Deconstruction with Discrete Embeddings R2RT 711 resource 131.11
39 Rohan & Lenny #3: Recurrent Neural Networks & LSTMs Rohan Kapur 741 tutorial 129.84
40 The Unreasonable Ineffectiveness of Deep Learning in NLU Suman Deb Roy 713 tutorial 129.45
41 Deep Learning in NLP Vered Shwartz 711 resource 129.26
42 Recurrent Neural Networks Stephen Grossberg 741 paper 128.43
43 Your tl;dr by an ai: a deep reinforced model for abstractive summarization Romain Paulus 754 tutorial 127.32
44 Your tl;dr by an Ai: a Deep Reinforced Model for Abstractive Summarization Romain Paulus 811 resource 127.32
45 Deep Learning chatbots analysis - whats the actual tech behind them? Przemyslaw 756 tutorial 127.16
46 Generating Large Images from Latent Vectors Author Unknown 631 tutorial 126.91
47 Clustering cliques for graph-based summarization of the biomedical research literature Han Zhang, Marcelo Fiszman, Dongwook Shin, Bartomiej Wilkowski, Thomas Rindflesch 999 paper 126.90
48 Written Memories: Understanding, Deriving and Extending the LSTM R2RT 742 resource 126.37
49 Negated bio-events: analysis and identification Raheel Nawaz, Paul Thompson, Sophia Ananiadou 999 paper 126.36
50 A social network's changing statistical properties and the quality of human innovation Brian Uzzi 999 paper 124.99
51 Neural text generation: How to generate text using conditional language models Neil Yager 43 resource 124.65
52 The 8 Neural Network Architectures Machine Learning Researchers Need to Learn Nand Kishor 711 resource 124.10
53 What is the difference between convolutional neural networks, restricted Boltzmann machines, and auto-encoders? ffriend 744 tutorial 123.76
54 Towards data set augmentation with GANs Pedro Ferreira 713 resource 123.58
55 Ideas on interpreting machine learning Patrick Hall, Wen Phan, SriSatish Ambati 134 tutorial 123.52
56 Taming Recurrent Neural Networks for Better Summarization Abigail See 754 tutorial 123.45
57 Machine Learning for Humans Vishal Maini, Samer Sabri 134 tutorial 123.06
58 Word embeddings in 2017: Trends and future directions Sebastian Ruder 721 resource 122.98
59 Your TL;DR by an AI: A Deep Reinforced Model for Abstractive Summarization Romain Paulus, Caiming Xiong and Richard Socher 754 resource 122.86
60 Generative Adversarial Networks (GANs): Engine and Applications Anton Karazeev 713 resource 122.39
61 An Overview of Multi-Task Learning in Deep Neural Networks Sebastian Ruder 829 tutorial 122.20
62 Text Segmentation based on Semantic Word Embeddings Alexander Alemi, Paul Ginsparg 721 library 122.15
63 Multi-Task Learning Objectives for Natural Language Processing Author Unknown 133 resource 122.05
64 Introduction to Neural Machine Translation with GPUs (part 3) Kyunghyun Cho 753 tutorial 122.02
65 Machine Translation Without the Data Harshvardhan Gupta 451 resource 121.98
66 How do we capture structure in relational data? Matthew Das Sarma 711 resource 121.89
67 Generative Model Chatbots Kumar Shridhar 756 tutorial 121.49
68 Advances in Semantic Textual Similarity Yinfei Yang, Chris Tar 311 resource 121.48
69 Awesome - Most Cited Deep Learning Papers Terry Taewoong Um 713 resource 121.35
70 State-of-the-art neural coreference resolution for chatbots Thomas Wolf 756 tutorial 121.04
71 Deep Learning Achievements Over the Past Year Eduard Tyantov 711 resource 120.99
72 Adversarial Autoencoders (with Pytorch) Felipe N. Ducau 713 tutorial 120.86
73 The 8 Neural Network Architectures Machine Learning Researchers Need to Learn James Le' 731 resource 120.83
74 Improving Language Understanding with Unsupervised Learning Alec Radford 581 resource 120.07
75 Minibatch Metropolis-Hastings Daniel Seita 107 tutorial 119.93
76 Gimli: open source and high-performance biomedical name recognition David Campos, Sergio Matos, Jose Oliveira 999 paper 119.90
77 Deep Learning 2: Part 1 Lesson 4 Hiromi Suenaga 711 resource 119.45
78 The Building Blocks of Interpretability Chris Olah 614 resource 119.28
79 A general framework for analysing diversity in science, technology and society Andy Stirling 999 paper 119.06
80 Recurrent Neural Networks: The Powerhouse of Language Modeling James Le 741 resource 119.02
81 Image Completion with Deep Learning in TensorFlow Brandon Amos 731 tutorial 118.95
82 Improving End-to-End Models for Speech Recognition Tara Sainath 945 resource 118.45
83 The NeuroEvolution of Augmenting Topologies (NEAT) Users Page Author Unknown 999 resource 118.42
84 A miscellany of fun deep learning papers Adrian Colyer 711 resource 117.82
85 The Unreasonable Effectiveness of Recurrent Neural Networks Andrej Karpathy 741 survey 116.69
86 An Introduction to Generative Adversarial Networks (with code in TensorFlow) John Glover 731 tutorial 116.56
87 Learned in translation: contextualized word vectors Bryan McCann 452 resource 116.39
88 Gensim integration with scikit-learn and Keras Chinmaya Pancholi 713 library 116.36
89 SippyCup Unit 2: Travel queries Bill MacCartney 365 tutorial 116.23
90 Deep Generative Models Prakash Pandey 711 resource 116.06
91 Four deep learning trends from ACL 2017: Part 1 Abigail See 713 resource 115.82
92 The Neural Network Zoo Fjodor Van Veen 712 tutorial 115.22