Seq2seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models

@article{Strobelt2018Seq2seqVisAV,
  title={Seq2seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models},
  author={Hendrik Strobelt and Sebastian Gehrmann and Michael Behrisch and Adam Perer and Hanspeter Pfister and Alexander M. Rush},
  journal={IEEE Transactions on Visualization and Computer Graphics},
  year={2018},
  volume={25},
  pages={353-363}
}
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… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 43 CITATIONS

A Multiscale Visualization of Attention in the Transformer Model

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Visualizing Attention in Transformer-Based Language Representation Models

  • Jesse Vig
  • Mathematics, Computer Science
  • ArXiv
  • 2019
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures

VIEW 1 EXCERPT
CITES BACKGROUND

AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models

VIEW 1 EXCERPT
CITES BACKGROUND

Analyzing the Structure of Attention in a Transformer Language Model

VIEW 2 EXCERPTS
CITES METHODS

Detecting and Reducing Bias in a High Stakes Domain

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 55 REFERENCES

ConceptVector: Text Visual Analytics via Interactive Lexicon Building Using Word Embedding

VIEW 1 EXCERPT

Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers

VIEW 1 EXCERPT