Querying NoSQL with Deep Learning to Answer Natural Language Questions

Almost all of today’s knowledge is stored in databases and thus can only be accessed with the help of domain specific query languages, strongly limiting the number of people which can access the data. In this work, we demonstrate an end-to-end trainable question answering (QA) system that allows a user to query an external NoSQL database by using natural language. A major challenge of such a system is the non-differentiability of database operations which we overcome by applying policy-based reinforcement learning. We evaluate our approach on Facebook’s bAbI Movie Dialog dataset and achieve a competitive score of 84.2% compared to several benchmark models. We conclude that our approach excels with regard to real-world scenarios where knowledge resides in external databases and intermediate labels are too costly to gather for non-end-to-end trainable QA systems.

[1]  Xiang Zhang,et al.  Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems , 2015, ICLR.

[2]  Chen Liang,et al.  Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision , 2016, ACL.

[3]  Anil A. Bharath,et al.  Deep Reinforcement Learning: A Brief Survey , 2017, IEEE Signal Processing Magazine.

[4]  Christopher D. Manning,et al.  A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue , 2017, EACL.

[5]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[6]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[7]  Jason Weston,et al.  Large-scale Simple Question Answering with Memory Networks , 2015, ArXiv.

[8]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Richard Socher,et al.  Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning , 2018, ArXiv.

[11]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[12]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Joelle Pineau,et al.  A Survey of Available Corpora for Building Data-Driven Dialogue Systems , 2015, Dialogue Discourse.

[14]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[15]  Dawn Xiaodong Song,et al.  SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning , 2017, ArXiv.

[16]  Jürgen Schmidhuber,et al.  Evolving large-scale neural networks for vision-based reinforcement learning , 2013, GECCO '13.

[17]  J. Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM networks , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[18]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[19]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[20]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[21]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[22]  Hang Li,et al.  Coupling Distributed and Symbolic Execution for Natural Language Queries , 2016, ICML.

[23]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[24]  Ilya Kostrikov,et al.  Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play , 2017, ICLR.

[25]  Jianfeng Gao,et al.  Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access , 2016, ACL.

[26]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[27]  Vysoké Učení,et al.  Statistical Language Models Based on Neural Networks , 2012 .

[28]  Giuseppe Riccardi,et al.  How may I help you? , 1997, Speech Commun..

[29]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

[30]  Jason Weston,et al.  ParlAI: A Dialog Research Software Platform , 2017, EMNLP.

[31]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[32]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[33]  Christopher D. Manning,et al.  Key-Value Retrieval Networks for Task-Oriented Dialogue , 2017, SIGDIAL Conference.

[34]  Zhoujun Li,et al.  Building Task-Oriented Dialogue Systems for Online Shopping , 2017, AAAI.

[35]  Joseph Weizenbaum,et al.  ELIZA—a computer program for the study of natural language communication between man and machine , 1966, CACM.

[36]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[37]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[38]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[39]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[40]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[41]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[42]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

[43]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[44]  Julia Hirschberg,et al.  Error handling in spoken dialogue systems , 2005, Speech Commun..

[45]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[46]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[47]  Sepp Hochreiter,et al.  Untersuchungen zu dynamischen neuronalen Netzen , 1991 .

[48]  Tsung-Hsien Wen,et al.  Neural Belief Tracker: Data-Driven Dialogue State Tracking , 2016, ACL.

[49]  Shahrokh Valaee,et al.  Recent Advances in Recurrent Neural Networks , 2017, ArXiv.

[50]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[51]  Jianfeng Gao,et al.  End-to-End Task-Completion Neural Dialogue Systems , 2017, IJCNLP.

[52]  S. C. Kremer,et al.  Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[53]  Kenneth Mark Colby,et al.  Clinical artificial intelligence , 1981, Behavioral and Brain Sciences.

[54]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[55]  Ameya Nayak.  Type of NOSQL Databases and its Comparison with Relational Databases , 2013 .

[56]  Yishay Mansour,et al.  Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.

[57]  Homa B. Hashemi,et al.  Query Intent Detection using Convolutional Neural Networks , 2016 .

[58]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[59]  Jiliang Tang,et al.  A Survey on Dialogue Systems: Recent Advances and New Frontiers , 2017, SKDD.

[60]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[61]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[62]  Jason Weston,et al.  Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks , 2015, ICLR.

[63]  Mirella Lapata,et al.  Language to Logical Form with Neural Attention , 2016, ACL.

[64]  Andrew Chou,et al.  Semantic Parsing on Freebase from Question-Answer Pairs , 2013, EMNLP.

[65]  Jason Weston,et al.  Key-Value Memory Networks for Directly Reading Documents , 2016, EMNLP.

[66]  Christopher D. Manning,et al.  Cs224n Natural Language Processing With Deep Learning , 2017 .

[67]  Matthew Henderson,et al.  Deep Neural Network Approach for the Dialog State Tracking Challenge , 2013, SIGDIAL Conference.

[68]  T. L. Lai Andherbertrobbins.  Asymptotically Efficient Adaptive Allocation Rules , 2022 .

[69]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[70]  Neal Leavitt,et al.  Will NoSQL Databases Live Up to Their Promise? , 2010, Computer.

[71]  Charu C. Aggarwal,et al.  Neural Networks and Deep Learning , 2018, Springer International Publishing.

[72]  Jürgen Schmidhuber,et al.  Recurrent nets that time and count , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[73]  Gerald Tesauro,et al.  Practical issues in temporal difference learning , 1992, Machine Learning.

[74]  Murray Campbell,et al.  Deep Blue , 2002, Artif. Intell..

[75]  Jason Weston,et al.  Memory Networks , 2014, ICLR.

[76]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[77]  Yi Yang,et al.  WikiQA: A Challenge Dataset for Open-Domain Question Answering , 2015, EMNLP.

[78]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[79]  Jason Weston,et al.  Question Answering with Subgraph Embeddings , 2014, EMNLP.

[80]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[81]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[82]  Geoffrey Zweig,et al.  End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning , 2016, ArXiv.

[83]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[84]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[85]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[86]  Donald Michie,et al.  BOXES: AN EXPERIMENT IN ADAPTIVE CONTROL , 2013 .

[87]  James H. Martin,et al.  Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition , 2000 .

[88]  Percy Liang,et al.  Learning executable semantic parsers for natural language understanding , 2016, Commun. ACM.

[89]  Michael L. Littman,et al.  A theoretical analysis of Model-Based Interval Estimation , 2005, ICML.

[90]  Navdeep Jaitly,et al.  Hybrid speech recognition with Deep Bidirectional LSTM , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[91]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[92]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[93]  NAVID YAGHMAZADEH,et al.  SQLizer: query synthesis from natural language , 2017, Proc. ACM Program. Lang..

[94]  F. E..  A Relational Model of Data Large Shared Data Banks , 2000 .