View Project


Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access


This paper proposes KB-InfoBot — a multi-turn dialogue agent w hich helps users search Knowledge Bases (KBs) without composing complicated queries. Such goal-oriented dialogue agents typically need to interact with an external database to a ccess real-world knowledge. Previous systems achieved this by issuing a symbolic query to the KB to retrieve entries based on their attributes. However, such symbolic operations break the differ entiability of the system and prevent end-to-end training of neural dialogue agents. In this paper, we address this limitation by replacing symbolic queries with an induced “soft” posterior dist ribution over the KB that indicates which entities the user is interested in. Integrating the soft retrieval process with a reinforcement learner leads to higher task success rate and reward in both s imulations and against real users. We also present a fully neural end-to-end agent, trained entirely from user feedback, and discuss its application towards personalized dialogue agents.



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 DEEP LEARNING FOR CHATBOTS, PART 1 - INTRODUCTION Denny Britz 445 tutorial 202.09
2 NLP’s generalization problem, and how researchers are tackling it Ana Marasovic 711 resource 165.06
3 Highlights of EMNLP 2017: Exciting Datasets, Return of the Clusters, and More! Sebastian Ruder 641 resource 164.87
4 Rohan #2: Artificial intelligence, ?Progress/?Time Rohan Kapur 811 tutorial 156.28
5 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 232 survey 154.33
6 Building Cross-Lingual End-to-End Product Search with Tensorflow Han Xiao 731 resource 153.07
7 Deep Learning for NLP: An Overview of Recent Trends Elvis 711 resource 149.81
8 Artificial Intelligence’s Next Big Step: Reinforcement Learning Mary Branscombe 857 resource 141.88
9 Recurrent Neural Networks Tutorial, Part 1 - Introduction to RNNs Denny Britz 741 tutorial 140.80
10 The Definitive Guide to Natural Language Processing Javier Couto 133 tutorial 140.18
11 Introduction to Learning to Trade with Reinforcement Learning Denny Britz 857 resource 139.87
12 Recurrent Neural Network Tutorial, Part 4 – Implementing a GRU/LSTM RNN with Python and Theano Denny Britz 742 tutorial 136.38
13 Recent Advances in Document Summarization Jin-ge Yao, Xiaojun Wan, Jianguo Xiao 421 survey 133.94
14 Summaries and notes on Deep Learning research papers Denny Britz 713 resource 133.75
15 Simple Beginner’s guide to Reinforcement Learning & its implementation Faizan Shaikh 713 tutorial 133.33
16 Deconstruction with Discrete Embeddings R2RT 711 resource 131.95
17 Deep Learning Achievements Over the Past Year Eduard Tyantov 711 resource 131.74
19 Recurrent Neural Networks Tutorial, Part 2 - Implementing a RNN with Python, Numpy, and Theano Denny Britz 741 tutorial 130.56
20 The 7 NLP Techniques That Will Change How You Communicate in the Future (Part I) James Le 112 resource 130.46
21 The bAbI project Facebook 134 resource 130.16
22 The bAbI project Jason Weston, Antoine Bordes, Sumit Chopra, Alexander M. Rush, Bart van Merriënboer, Armand Joulin and Tomas Mikolov 755 tutorial 130.16
23 Chatsbots with Machine Learning: Building Neural Conversational Agents Dmitry Persiyanov 999 resource 128.85
24 Machine Learning for Humans Vishal Maini, Samer Sabri 134 tutorial 127.91
25 A Comparative Analysis of ChatBots APIs Author Unknown 921 resource 127.86
26 State-of-the-art neural coreference resolution for chatbots Thomas Wolf 756 tutorial 127.60
27 Recurrent Neural Networks Tutorial, Part 3- Backpropagation Through Time and Vanishing Gradients Denny Britz 741 tutorial 127.50
28 ACL 2017 Report Yuta Kikuchi, Sosuke Kobayashi 711 resource 126.89
29 Negated bio-events: analysis and identification Raheel Nawaz, Paul Thompson, Sophia Ananiadou 999 paper 126.81
30 Generative Models Andrej Karpathy, Pieter Abbeel, Greg Brockman, Peter Chen, Vicki Cheung, Rocky Duan, Ian Goodfellow, Durk Kingma, Jonathan Ho, Rein Houthooft, Tim Salimans, John Schulman, Ilya Sutskever, Wojciech Zar 756 resource 126.61
31 Analyzing the Meaning of Sentences Steven Bird, Ewan Klein, Edward Loper 721 course 125.48
32 Similarity-driven Semantic Role Induction via Graph Partitioning Joel Lang, Mirella Lapata 999 paper 125.00
33 Diversity and network coherence as indicators of interdisciplinarity: case studies in bionanoscience Ismael Rafols, Martin Meyer 999 paper 124.38
34 Rules of Machine Learning: Best Practices for ML Engineering Martin Zinkevich 711 resource 123.49
35 Clustering cliques for graph-based summarization of the biomedical research literature Han Zhang, Marcelo Fiszman, Dongwook Shin, Bartomiej Wilkowski, Thomas Rindflesch 999 paper 123.21
36 Getting Ready for AI based gaming agents - Overview of Open Source Reinforcement Learning Patterns Faizan Shaikh 713 resource 122.80
37 Transfer Learning - Machine Learnings Next Frontier Sebastian Ruder 978 tutorial 122.72
38 Prodigy: A new tool for radically efficient machine teaching Matthew Honnibal, Ines Montani 134 resource 122.07
39 How do we capture structure in relational data? Matthew Das Sarma 711 resource 121.32
40 Learning to Communicate Pieter Abbeel, Igor Mordatch, Ryan Lowe, Jon Gauthier & Jack Clark 861 tutorial 119.58
41 Neural Text Embeddings for IR Bhaskar Mitra, Nick Craswell 721 tutorial 119.25
42 Reinforcement Learning and DQN, learning to play from pixels Ruben Fiszel 857 tutorial 118.75
43 The Future (and Present) of Artificial Intelligence AMA Various Authors 811 resource 116.87
44 Reinforcement Learning Florentin Woergoetter, Bernd Porr 857 paper 115.55
45 Codra: A Novel Discriminative Framework for Rhetorical Analysis Shafiq Joty, Giuseppe Carenini, Raymond T. Ng 999 paper 114.38
46 Do Altmetrics Work? Twitter and Ten Other Social Web Services Mike Thelwall, Stefanie Haustein, Vincent Larivière, Cassidy R. Sugimoto 999 paper 113.65
47 The Evolution and Core Concepts of Deep Learning & Neural Networks Guest Blog 711 tutorial 113.23
48 Implementing the DistBelief Deep Neural Network Training Framework with Akka Alex Minnaar 713 tutorial 113.22
49 The long game towards understanding dialog Alexandre Lebrun, Antoine Bordes, Leon Bottou, Marco Baroni 756 resource 113.20
50 A Dozen Times Artificial Intelligence Startled the World Sumeet Agrawal 811 resource 112.65
51 A Beginner's Guide to Reinforcement Learning (for Java) Adam Gibson, Chris Nicholson, Josh Patterson 857 resource 112.07
52 Machine Learning For Beginners Divyansh Dwivedi 711 resource 111.41
53 The data that transformed AI research—and possibly the world Dave Gershgorn 107 resource 111.07
54 Machine Learning for Humans Vishal Maini 711 resource 110.07
55 Deep Learning for NLP, advancements and trends in 2017 Javier 711 resource 109.85
56 Deep Learning for Computer Vision - Introduction to Convolution Neural Networks Aarshay Jain 744 tutorial 109.61
57 Supervised learning is great — it’s data collection that’s broken Ines Montani, Matthew Honnibal 134 tutorial 109.41
58 Your TL;DR by an AI: A Deep Reinforced Model for Abstractive Summarization Romain Paulus, Caiming Xiong and Richard Socher 754 resource 109.37
59 An index to quantify an individual’s scientific research output that takes into account the effect of multiple coauthorship J. E. Hirsch 999 paper 109.31
60 A general framework for analysing diversity in science, technology and society Andy Stirling 999 paper 109.09
61 Under the Hood with Reinforcement Learning – Understanding Basic RL Models Bill Vorhies 857 resource 108.82
62 Demystifying Deep Reinforcement Learning Tambet Matiisen 857 tutorial 108.66
63 Machine Learning for Humans, Part 5: Reinforcement Learning Vishal Maini 711 resource 108.56
64 Machine Learning for Humans, Part 5: Reinforcement Learning Vishal Maini 713 resource 108.55
65 The Conversational Intelligence Challenge na 863 resource 108.31
66 ICML+ACL’18: Structure Back in Play, Translation Wants More Context Andre Martins 956 resource 107.89
67 Introduction to Neural Machine Translation with GPUs (part 3) Kyunghyun Cho 753 tutorial 107.50
68 DeepMind has a bigger plan for its newest Go-playing AI Dave Gershgorn 811 resource 107.46
69 A Practitioner's Guide to Natural Language Processing (Part I)?—?Processing & Understanding Text Dipanjan (DJ) Sarker 112 resource 107.43