Understanding Hidden Memories of Recurrent Neural Networks
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Memory visualization for gated recurrent neural networks in speech recognition2017
- Long-Term Recurrent Convolutional Networks for Visual Recognition and DescriptionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Squares: Supporting Interactive Performance Analysis for Multiclass ClassifiersIEEE Transactions on Visualization and Computer Graphics, 2016
- NameClarifier: A Visual Analytics System for Author Name DisambiguationIEEE Transactions on Visualization and Computer Graphics, 2016
- LSTM: A Search Space OdysseyIEEE Transactions on Neural Networks and Learning Systems, 2016
- A Five-Level Design Framework for Bicluster VisualizationsIEEE Transactions on Visualization and Computer Graphics, 2014
- Bixplorer: Visual Analytics with BiclustersComputer, 2013
- PivotPaths: Strolling through Faceted Information SpacesIEEE Transactions on Visualization and Computer Graphics, 2012
- Improved Similarity Trees and their Application to Visual Data ClassificationIEEE Transactions on Visualization and Computer Graphics, 2011
- Biclustering algorithms for biological data analysis: a surveyIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2004