Seq2Seq-VIS : A Visual Debugging Tool for Sequence-to-Sequence Models

Picture of Sebastian Gehrmann
Sebastian Gehrmann
Picture of Michael Behrisch
Michael Behrisch
Picture of Hanspeter Pfister
Hanspeter Pfister
Picture of Alexander Rush
Alexander Rush
Published at VAST | Berlin, Germany 2018
  • Best Paper Honorable Mention
Teaser image

Abstract

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.

Materials