/paragraph-detective

A library to identify paragraphs from a multiline extracted text (typically a pdf extractor). It uses machine learning to identify them through a set of examples and features.

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

para-detective

A library to identify paragraphs from a multiline extracted text (typically a pdf extractor). It uses machine learning to identify them through a set of examples and features.