The Open Book Genome Project is an open, community effort to enable deeper, more hollistic understanding of a book's unique characteristics.
Anyone can try sequencing an open access book using the OBGP Sequencer™ Google Colab Notebook. This interactive notebook runs directly within the browser, no installation required.
Once one has a book genome, there's a lot one can do. One can calculate the reading level of books. One can also extract book identifiers, perform Named-Entity Recognition (NER) of people, places, and subjects, identify themes, produce summaries, train language models (like word2vec) extract urls and citations, identify important pages, like glossaries and tables of contents, and even talk to books.
|Mek <email@example.com>||Internet Archive / OpenLibrary.org|
|Nolan Windham||Student at Claremont McKenna College|
|Drini Cami||Internet Archive / OpenLibrary.org|