Seq2seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models

Neural sequence-to-sequence models have proven to be accurate and robust for many sequence prediction tasks, and have become the standard approach for automatic translation of text. The models work with a five-stage blackbox pipeline that begins with encoding a source sequence to a vector space and then decoding out to a new target sequence. This process is now standard, but like many deep learning methods remains quite difficult to understand or debug. In this work, we present a visual analysis tool that allows interaction and “what if”-style exploration of trained sequence-to-sequence models through each stage of the translation process. The aim is to identify which patterns have been learned, to detect model errors, and to probe the model with counterfactual scenario. We demonstrate the utility of our tool through several real-world sequence-to-sequence use cases on large-scale models.

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

[2]  Andrew Slavin Ross,et al.  Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations , 2017, IJCAI.

[3]  Niklas Elmqvist,et al.  ConceptVector: Text Visual Analytics via Interactive Lexicon Building Using Word Embedding , 2018, IEEE Transactions on Visualization and Computer Graphics.

[4]  Mauro Cettolo,et al.  WIT3: Web Inventory of Transcribed and Translated Talks , 2012, EAMT.

[5]  Martin Wattenberg,et al.  Direct-Manipulation Visualization of Deep Networks , 2017, ArXiv.

[6]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[7]  Zhen Li,et al.  Understanding Hidden Memories of Recurrent Neural Networks , 2017, 2017 IEEE Conference on Visual Analytics Science and Technology (VAST).

[8]  Philipp Koehn,et al.  Six Challenges for Neural Machine Translation , 2017, NMT@ACL.

[9]  Bowen Zhou,et al.  Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond , 2016, CoNLL.

[10]  Minsuk Kahng,et al.  ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models , 2017, IEEE Transactions on Visualization and Computer Graphics.

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

[12]  Dylan Cashman,et al.  RNNbow: Visualizing Learning Via Backpropagation Gradients in RNNs , 2018, IEEE Computer Graphics and Applications.

[13]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[14]  J. Kruskal.  Nonmetric multidimensional scaling: A numerical method , 1964 .

[15]  Jason Weston,et al.  A Neural Attention Model for Abstractive Sentence Summarization , 2015, EMNLP.

[16]  Alexander M. Rush,et al.  LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks , 2016, IEEE Transactions on Visualization and Computer Graphics.

[17]  Rasmus Rothe,et al.  Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers , 2017, 1705.05627.

[18]  Jun-Seok Kim,et al.  Interactive Visualization and Manipulation of Attention-based Neural Machine Translation , 2017, EMNLP.

[19]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[20]  Emily Chen,et al.  How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation , 2018, ArXiv.

[21]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[22]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[23]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

[24]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[25]  Jeff Johnson,et al.  Billion-Scale Similarity Search with GPUs , 2017, IEEE Transactions on Big Data.

[26]  Max Welling,et al.  Visualizing Deep Neural Network Decisions: Prediction Difference Analysis , 2017, ICLR.

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

[28]  Arvind Satyanarayan,et al.  The Building Blocks of Interpretability , 2018 .

[29]  Minsuk Kahng,et al.  Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers , 2018, IEEE Transactions on Visualization and Computer Graphics.

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

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

[32]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[33]  Martin Wattenberg,et al.  Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation , 2016, TACL.

[34]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[35]  Regina Barzilay,et al.  Rationalizing Neural Predictions , 2016, EMNLP.

[36]  Iryna Gurevych,et al.  End-to-End Non-Factoid Question Answering with an Interactive Visualization of Neural Attention Weights , 2017, ACL.

[37]  Marc'Aurelio Ranzato,et al.  Building high-level features using large scale unsupervised learning , 2011, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[38]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[39]  Shan Carter,et al.  Attention and Augmented Recurrent Neural Networks , 2016 .

[40]  Lukasz Kaiser,et al.  Generating Wikipedia by Summarizing Long Sequences , 2018, ICLR.

[41]  Yann Dauphin,et al.  Convolutional Sequence to Sequence Learning , 2017, ICML.

[42]  Yann Dauphin,et al.  A Convolutional Encoder Model for Neural Machine Translation , 2016, ACL.

[43]  Or Biran,et al.  Explanation and Justification in Machine Learning : A Survey Or , 2017 .

[44]  Hod Lipson,et al.  Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.

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

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

[47]  Lijun Wu,et al.  Achieving Human Parity on Automatic Chinese to English News Translation , 2018, ArXiv.

[48]  Kenney Ng,et al.  Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models , 2016, CHI.

[49]  Dylan Cashman,et al.  RNNbow: Visualizing Learning Via Backpropagation Gradients in RNNs , 2018, IEEE Computer Graphics and Applications.

[50]  Daniel Jurafsky,et al.  Understanding Neural Networks through Representation Erasure , 2016, ArXiv.

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

[52]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[53]  Yang Liu,et al.  Visualizing and Understanding Neural Machine Translation , 2017, ACL.

[54]  Tommi S. Jaakkola,et al.  A causal framework for explaining the predictions of black-box sequence-to-sequence models , 2017, EMNLP.