![Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models](https://vcg.seas.harvard.edu/content/3-publications/20181031-seq2seq-vis-a-visual-debugging-tool-for-sequence-to-sequence-models/strobelt2018.png)
Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
IEEE transactions on visualization and computer graphics, 2018.
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 in a five stage blackbox process that involves 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 with a trained sequence-to-sequence model through each stage of the translation process. The aim is to identify which patterns have been learned and to detect model errors.