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 225.26
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 221.13
3 NLP’s generalization problem, and how researchers are tackling it Ana Marasovic 711 resource 218.77
4 Rohan #2: Artificial intelligence, ?Progress/?Time Rohan Kapur 811 tutorial 207.37
5 Highlights of EMNLP 2017: Exciting Datasets, Return of the Clusters, and More! Sebastian Ruder 641 resource 198.41
6 A Beginner’s Guide to Deep Reinforcement Learning Adam Gibson, Chris Nicholson, Josh Patterson 857 library 190.28
7 Recent Advances in Document Summarization Jin-ge Yao, Xiaojun Wan, Jianguo Xiao 421 survey 188.24
8 Clustering cliques for graph-based summarization of the biomedical research literature Han Zhang, Marcelo Fiszman, Dongwook Shin, Bartomiej Wilkowski, Thomas Rindflesch 999 paper 182.54
9 Deep Learning for NLP: An Overview of Recent Trends Elvis 711 resource 176.21
10 Building Cross-Lingual End-to-End Product Search with Tensorflow Han Xiao 731 resource 175.86
11 The Definitive Guide to Natural Language Processing Javier Couto 133 tutorial 173.00
12 Machine Learning for Humans Vishal Maini, Samer Sabri 134 tutorial 170.67
13 Analyzing the Meaning of Sentences Steven Bird, Ewan Klein, Edward Loper 721 course 170.25
14 Introduction to Learning to Trade with Reinforcement Learning Denny Britz 857 resource 168.25
15 Simple Beginner’s guide to Reinforcement Learning & its implementation Faizan Shaikh 713 tutorial 167.67
16 Similarity-driven Semantic Role Induction via Graph Partitioning Joel Lang, Mirella Lapata 999 paper 167.35
17 Codra: A Novel Discriminative Framework for Rhetorical Analysis Shafiq Joty, Giuseppe Carenini, Raymond T. Ng 999 paper 166.27
18 The 7 NLP Techniques That Will Change How You Communicate in the Future (Part I) James Le 112 resource 166.06
19 Summaries and notes on Deep Learning research papers Denny Britz 713 resource 165.72
20 Recurrent Neural Networks Tutorial, Part 1 - Introduction to RNNs Denny Britz 741 tutorial 165.67
21 Artificial Intelligence’s Next Big Step: Reinforcement Learning Mary Branscombe 857 resource 162.11
22 Recurrent Neural Network Tutorial, Part 4 – Implementing a GRU/LSTM RNN with Python and Theano Denny Britz 742 tutorial 161.13
23 The Future (and Present) of Artificial Intelligence AMA Various Authors 811 resource 160.63
24 Deconstruction with Discrete Embeddings R2RT 711 resource 160.03
25 A Comparative Analysis of ChatBots APIs Author Unknown 921 resource 157.68
26 Chatsbots with Machine Learning: Building Neural Conversational Agents Dmitry Persiyanov 999 resource 155.58
27 Deep Learning Achievements Over the Past Year Eduard Tyantov 711 resource 155.18
28 State-of-the-art neural coreference resolution for chatbots Thomas Wolf 756 tutorial 154.67
30 Negated bio-events: analysis and identification Raheel Nawaz, Paul Thompson, Sophia Ananiadou 999 paper 154.63
31 The Evolution and Core Concepts of Deep Learning & Neural Networks Guest Blog 711 tutorial 154.48
32 How do we capture structure in relational data? Matthew Das Sarma 711 resource 153.29
33 Rules of Machine Learning: Best Practices for ML Engineering Martin Zinkevich 711 resource 152.64
34 Diversity and network coherence as indicators of interdisciplinarity: case studies in bionanoscience Ismael Rafols, Martin Meyer 999 paper 152.61
35 Transfer Learning - Machine Learnings Next Frontier Sebastian Ruder 978 tutorial 152.54
36 Recurrent Neural Networks Tutorial, Part 2 - Implementing a RNN with Python, Numpy, and Theano Denny Britz 741 tutorial 152.37
37 The bAbI project Jason Weston, Antoine Bordes, Sumit Chopra, Alexander M. Rush, Bart van Merriënboer, Armand Joulin and Tomas Mikolov 755 tutorial 151.53
38 The bAbI project Facebook 134 resource 151.53
39 Neural Text Embeddings for IR Bhaskar Mitra, Nick Craswell 721 tutorial 151.43
40 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 149.99
41 Implementing the DistBelief Deep Neural Network Training Framework with Akka Alex Minnaar 713 tutorial 149.96
42 ACL 2017 Report Yuta Kikuchi, Sosuke Kobayashi 711 resource 149.16
43 Prodigy: A new tool for radically efficient machine teaching Matthew Honnibal, Ines Montani 134 resource 148.91
44 ParlAI FAIR 753 library 146.24
45 parlai 0.1.0 Alexander H Miller 756 library 145.58
46 Your TL;DR by an AI: A Deep Reinforced Model for Abstractive Summarization Romain Paulus, Caiming Xiong and Richard Socher 754 resource 145.49
47 Deep Learning for Computer Vision - Introduction to Convolution Neural Networks Aarshay Jain 744 tutorial 145.25
48 Recurrent Neural Networks Tutorial, Part 3- Backpropagation Through Time and Vanishing Gradients Denny Britz 741 tutorial 145.15
49 Do Altmetrics Work? Twitter and Ten Other Social Web Services Mike Thelwall, Stefanie Haustein, Vincent Larivière, Cassidy R. Sugimoto 999 paper 144.71
50 Getting Ready for AI based gaming agents - Overview of Open Source Reinforcement Learning Patterns Faizan Shaikh 713 resource 143.58
51 Quora Duplicate Questions Corpus Quora 151 corpus 142.85
52 DeepPavlov deepmipt 811 library 142.78
53 Lexicalization and Generative Power in Ccg Marco Kuhlmann, Alexander Koller, Giorgio Satta 999 paper 142.75
54 A large-scale community structure analysis in Facebook Emilio Ferrara 999 paper 142.43
55 Introduction to Neural Machine Translation with GPUs (part 3) Kyunghyun Cho 753 tutorial 141.31
56 Literature Mining for the Discovery of Hidden Connections between Drugs, Genes and Diseases Frijters, Raoul AND van Vugt, Marianne AND Smeets, Ruben AND van Schaik, René AND de Vlieg, Jacob AND Alkema, Wynand 999 paper 140.91
57 Reinforcement Learning Florentin Woergoetter, Bernd Porr 857 paper 140.21
58 News Article Wikipedia Dataset Author Unknown 999 library 139.75
59 Reinforcement Learning and DQN, learning to play from pixels Ruben Fiszel 857 tutorial 139.71
60 Gensim integration with scikit-learn and Keras Chinmaya Pancholi 713 library 138.89
61 An Overview of Multi-Task Learning in Deep Neural Networks Sebastian Ruder 829 tutorial 138.79
62 Open Machine Learning Course. Topic 3. Classification, Decision Trees and k Nearest Neighbors Yury Kashnitskiy 711 resource 138.34
63 Awesome Python Vinta 131 resource 138.26
64 Bayesian Statistics explained to Beginners in Simple English NSS 102 tutorial 138.08
65 Demystifying Deep Reinforcement Learning Tambet Matiisen 857 tutorial 137.96
66 Deep Learning for NLP, advancements and trends in 2017 Javier 711 resource 137.40
67 Learning to Communicate Pieter Abbeel, Igor Mordatch, Ryan Lowe, Jon Gauthier & Jack Clark 861 tutorial 137.06
68 Maluuba Frames Datasets Maluuba Frames 999 corpus 136.32
69 Machine Learning For Beginners Divyansh Dwivedi 711 resource 136.24
70 The history and meaning of the journal impact factor Eugene Garfield 999 paper 136.02
71 A general framework for analysing diversity in science, technology and society Andy Stirling 999 paper 135.74
72 19 Data Science Tools for people who aren’t so good at Programming Aarshay Jain 107 tutorial 134.59
73 ICML+ACL’18: Structure Back in Play, Translation Wants More Context Andre Martins 956 resource 134.47
74 Under the Hood with Reinforcement Learning – Understanding Basic RL Models Bill Vorhies 857 resource 134.44
75 The NeuroEvolution of Augmenting Topologies (NEAT) Users Page Author Unknown 999 resource 134.40
76 Machine Learning for Humans Vishal Maini 711 resource 134.03
77 40 Interview Questions asked at Startups in Machine Learning / Data Science ANALYTICS VIDHYA CONTENT TEAM 107 tutorial 133.91
78 Ideas on interpreting machine learning Patrick Hall, Wen Phan, SriSatish Ambati 134 tutorial 133.86
79 Introduction to Semi-Supervised Learning Xiaojin Zhu and Andrew B. Goldberg 581 survey 133.78
80 A Dozen Times Artificial Intelligence Startled the World Sumeet Agrawal 811 resource 133.71
81 The Unreasonable Effectiveness of Recurrent Neural Networks Andrej Karpathy 741 survey 133.44
82 A New Multi-Turn Multi-Domain Task-Oriented Dialogue Dataset Stanford 756 corpus 133.03
83 Gimli: open source and high-performance biomedical name recognition David Campos, Sergio Matos, Jose Oliveira 999 paper 132.58
84 Supervised learning is great — it’s data collection that’s broken Ines Montani, Matthew Honnibal 134 tutorial 132.55
85 Deep Reinforcement Learning: Pong from Pixels Andrej Karpathy 857 tutorial 132.01
86 A First Taste of Machine Learning Terence Parr, Jeremy Howard 112 resource 132.00
87 A Practitioner's Guide to Natural Language Processing (Part I)?—?Processing & Understanding Text Dipanjan (DJ) Sarker 112 resource 131.98
88 Discriminative Syntax-based Word Ordering for Text Generation Yue Zhang, Stephen Clark 999 paper 131.78
89 An index to quantify an individual’s scientific research output that takes into account the effect of multiple coauthorship J. E. Hirsch 999 paper 131.62
90 Four deep learning trends from ACL 2017: Part 2 Abigail See 713 resource 131.55
91 The Building Blocks of Interpretability Chris Olah 614 resource 131.23
92 Natural Language Processing (NLP) for Computational Social Science Cristian Danescu-Niculescu-Mizil, Lillian Lee 133 tutorial 130.29
93 Artificial Intelligence Demystified Guest Blog 811 resource 129.82
94 Neural Nets for Generating Music Kyle McDonald 999 resource 129.49