Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
This tool helps researchers and practitioners debug and interpret sequence-to-sequence models, which are standard but opaque in deep learning.
The authors tackled the problem of understanding and debugging black-box sequence-to-sequence models by developing a visual analysis tool that allows interaction through each stage of the translation process, demonstrating its utility in real-world large-scale use cases.
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. We demonstrate the utility of our tool through several real-world large-scale sequence-to-sequence use cases.