TextDrill is an open-source project for analysis of unstructured text
TextDrill source code is published on github.com
You are free to use TextDrill in any way you want subject to Apache License, Version 2
We are not responsible for any damages or losses either direct or implied due to you using the tool
Please consult Apache License, Version 2 for details
TextDrill is based on methods for fast-embedding and clustering of text (language agnostic).
Blog Post on the Ngram Embedding Algorithm
Blog Post on the Clustering Algorithm
TextDrill can take advantage of state-of-the-art NLP capabilities for mainstream languages via preprocessors such as Spacy and HuggingFace (in development).
If you file bugs in the product, please use github to report them
We'll try to address them as soon as we can
If you want to give use feedback privately, please contact us at hello@mlstream.com
Thank you for making it all the way to here