Understanding Hidden Memories of Recurrent Neural Networks

Recurrent neural networks (RNNs) have been successfully applied to various natural language processing (NLP) tasks and achieved better results than conventional methods. However, the lack of understanding of the mechanisms behind their effectiveness limits further improvements on their architectures. In this paper, we present a visual analytics method for understanding and comparing RNN models for NLP tasks. We propose a technique to explain the function of individual hidden state units based on their expected response to input texts. We then co-cluster hidden state units and words based on the expected response and visualize co-clustering results as memory chips and word clouds to provide more structured knowledge on RNNs’ hidden states. We also propose a glyph-based sequence visualization based on aggregate information to analyze the behavior of an RNN’s hidden state at the sentence-level. The usability and effectiveness of our method are demonstrated through case studies and reviews from domain experts.

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

[2]  Arlindo L. Oliveira,et al.  Biclustering algorithms for biological data analysis: a survey , 2004, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[3]  Pascal Vincent,et al.  Visualizing Higher-Layer Features of a Deep Network , 2009 .

[4]  Angus Graeme Forbes.  Visualizing and Verifying Directed Social Queries , 2012 .

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

[6]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Kwan-Liu Ma,et al.  StarClass: Interactive Visual Classification using Star Coordinates , 2003, SDM.

[8]  Desney S. Tan,et al.  Interactive optimization for steering machine classification , 2010, CHI.

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

[10]  Thomas Brox,et al.  Inverting Visual Representations with Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Ting Liu,et al.  Document Modeling with Gated Recurrent Neural Network for Sentiment Classification , 2015, EMNLP.

[12]  Chris North,et al.  A Five-Level Design Framework for Bicluster Visualizations , 2014, IEEE Transactions on Visualization and Computer Graphics.

[13]  Chris North,et al.  Bixplorer: Visual Analytics with Biclusters , 2013, Computer.

[14]  John T. Stasko,et al.  Interactive visual co-cluster analysis of bipartite graphs , 2016, 2016 IEEE Pacific Visualization Symposium (PacificVis).

[15]  Feiping Nie,et al.  Linear Discriminative Star Coordinates for Exploring Class and Cluster Separation of High Dimensional Data , 2017, Comput. Graph. Forum.

[16]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[17]  Yanhong Wu,et al.  NameClarifier: A Visual Analytics System for Author Name Disambiguation , 2017, IEEE Transactions on Visualization and Computer Graphics.

[18]  Ben Shneiderman,et al.  The eyes have it: a task by data type taxonomy for information visualizations , 1996, Proceedings 1996 IEEE Symposium on Visual Languages.

[19]  Inderjit S. Dhillon,et al.  Co-clustering documents and words using bipartite spectral graph partitioning , 2001, KDD '01.

[20]  Visual Tools for Debugging Neural Language Models , 2016 .

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

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

[23]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[24]  Xinlei Chen,et al.  Visualizing and Understanding Neural Models in NLP , 2015, NAACL.

[25]  Jaegul Choo,et al.  iVisClassifier: An interactive visual analytics system for classification based on supervised dimension reduction , 2010, 2010 IEEE Symposium on Visual Analytics Science and Technology.

[26]  Jonathan C. Roberts,et al.  Visual comparison for information visualization , 2011, Inf. Vis..

[27]  Bongshin Lee,et al.  Squares: Supporting Interactive Performance Analysis for Multiclass Classifiers , 2017, IEEE Transactions on Visualization and Computer Graphics.

[28]  Alexander M. Rush,et al.  Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks , 2016, ArXiv.

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

[30]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[31]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[32]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[33]  Yang Feng,et al.  Memory visualization for gated recurrent neural networks in speech recognition , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[34]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[35]  Susan T. Dumais,et al.  PivotPaths: Strolling through Faceted Information Spaces , 2012, IEEE Transactions on Visualization and Computer Graphics.

[36]  Singh Vijendra,et al.  Feature Selection Using Classifier in High Dimensional Data , 2014, ArXiv.

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

[38]  James H. Martin,et al.  Speech and Language Processing, 2nd Edition , 2008 .

[39]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[40]  Rosane Minghim,et al.  Improved Similarity Trees and their Application to Visual Data Classification , 2011, IEEE Transactions on Visualization and Computer Graphics.

[41]  Slav Petrov,et al.  A Universal Part-of-Speech Tagset , 2011, LREC.

[42]  Giuseppe Carenini,et al.  ConVis: A Visual Text Analytic System for Exploring Blog Conversations , 2014, Comput. Graph. Forum.

[43]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[44]  Zhen Li,et al.  Towards Better Analysis of Deep Convolutional Neural Networks , 2016, IEEE Transactions on Visualization and Computer Graphics.

[45]  Paulo E. Rauber,et al.  Visualizing the Hidden Activity of Artificial Neural Networks , 2017, IEEE Transactions on Visualization and Computer Graphics.

[46]  Ewan Klein,et al.  Natural Language Processing with Python , 2009 .

[47]  Fei-Fei Li,et al.  Visualizing and Understanding Recurrent Networks , 2015, ArXiv.

[48]  Arthur Szlam,et al.  Automatic Rule Extraction from Long Short Term Memory Networks , 2016, ICLR.

[49]  Ashish Kapoor,et al.  FeatureInsight: Visual support for error-driven feature ideation in text classification , 2015, 2015 IEEE Conference on Visual Analytics Science and Technology (VAST).

[50]  Desney S. Tan,et al.  EnsembleMatrix: interactive visualization to support machine learning with multiple classifiers , 2009, CHI.

[51]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.