Skip to content

amauboussin/text-lime

Repository files navigation

Explaining the predictions of any (text) classifier

An extension of LIME Ribeiro et. al 2016 for text classification. The main pipeline trains words embeddings using fastText, add noises to embedding space of documents, and identifies important words by analyzing how the noise affects the output probabilities of any text classification model. The results are visualized in d3.js.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published