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

Citation:

Strobelt, H., et al., 2018. Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models. IEEE Transactions on Visualization and Computer Graphics.
vast_18_s2svis_paper_.pdf6.05 MB

Abstract:

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.

Publisher's Version

Last updated on 11/25/2019