An interest in shorthand or "short-writing" developed towards the end of the 16th century in England. In 1588, Timothy Bright published his Characterie; An Arte of Shorte, Swifte and Secrete Writing by Character which introduced a system with 500 arbitrary symbols each representing one word. Bright's book was followed by a number of others, including Peter Bales' The Writing Schoolemaster in 1590, John Willis's Art of Stenography in 1602, Edmond Willis's An abbreviation of writing by character in 1618, and Thomas Shelton's Short Writing in 1626 (later re-issued as Tachygraphy).
The new sokki were used to transliterate popular vernacular story-telling theater (yose) of the day. This led to a thriving industry of sokkibon (shorthand books). The ready availability of the stories in book form, and higher rates of literacy (which the very industry of sokkibon may have helped create, due to these being oral classics that were already known to most people) may also have helped kill the yose theater, as people no longer needed to see the stories performed in person to enjoy them. Sokkibon also allowed a whole host of what had previously been mostly oral rhetorical and narrative techniques into writing, such as imitation of dialect in conversations (which can be found back in older gensaku literature; but gensaku literature used conventional written language in between conversations, however).
NLP can be used to interpret free, unstructured text and make it analyzable. There is a tremendous amount of information stored in free text files, such as patients' medical records. Before deep learning-based NLP models, this information was inaccessible to computer-assisted analysis and could not be analyzed in any systematic way. With NLP analysts can sift through massive amounts of free text to find relevant information.