The app loads a BiLSTM model trained on literary texts and specifically on the English Litbank dataset (https://github.com/dbamman/litbank). It will work best on English texts from the 19th and 20th century.
The app features two pages
- one where the user can type or copy custom text into a field and
- one where the user can upload a txt file.
In both cases the text will be displayed with colour coded detected entities. The whole text and entities can then be downloaded in a csv file.