InteLiText

InteLiText

InteLiText is a text processing technology, based on natural language processing, that covers all phases required to enable searches over a documentary corpus with linguistically intelligent, surgical‑grade precision without affecting response times. These phases range from the digitization of books or documents, the extraction of metadata and textual content from diverse sources (digitized texts, PDF documents, manuscripts, web pages, ...), the contextualization of paragraphs, sentences, and words within each document, through to the creation of an intelligent search engine with a web-based or local interface over the processed documentary corpus. The projects created by the University Institute of Textual Analysis and Applications using InteLiText: Digitization and search engine with linguistic intelligence are: The Conversation, DiseCan and ModeCan. 

https://iatext.ulpgc.es/sites/default/files/InteLiText.pdfInteLiText PDF presentation