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

TL;DR

Seq2Seq-Vis is a visual debugging tool designed to help understand, analyze, and identify errors in sequence-to-sequence models by visualizing each stage of the translation process.

Contribution

The paper introduces a novel interactive visualization tool for debugging and understanding sequence-to-sequence models at each processing stage.

Findings

Enables identification of learned patterns and errors in models

Facilitates analysis of large-scale real-world sequence tasks

Improves interpretability of sequence-to-sequence models

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 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.