We explore two techniques which use color to make sense of statistical text models. One method uses in-text annotations to illustrate a model's view of particular tokens in particular documents. Another uses a high-level, "words-as-pixels" graphic to display an entire corpus. Together, these methods offer both zoomed-in and zoomed-out perspectives into a model's understanding of text. We show how these interconnected methods help diagnose a classifier's poor performance on Twitter slang, and make sense of a topic model on historical political texts.
Cite
@article{arxiv.1606.06352,
title = {Visualizing textual models with in-text and word-as-pixel highlighting},
author = {Abram Handler and Su Lin Blodgett and Brendan O'Connor},
journal= {arXiv preprint arXiv:1606.06352},
year = {2016}
}
Comments
Presented at 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), New York, NY