An arrangement and corresponding method are described for multi-domain natural
language processing. Multiple parallel domain pipelines are used for processing a natural …

Provided is a method including obtaining a corpus and an associated set of domain
indicators. The method includes learning a set of vectors in an embedding space based on n …

US PATENT DOCUMENTS 5,359,724. A 10, 1994 Earle 5,647,058 A 7/1997 Agrawal et al.
5,721,910 A 2/1998 Unger et al. 5,752,243 A 5, 1998 Reiter et al. 5,918,232 A 6, 1999 …

In a method for representing a text document with a graphical model, a document including
a plurality of ordered words is received and a graph data structure for the document is cre …

STORE ASSOCIATIONS WITH BOTH TEMPLATE AND OBJECT record in the database. A
unique identi? cation code is assigned to the record including a reference to the template …

Embodiments are directed towards providing a device and method of identifying media
items from a media library maintained by a media server that are similar to a designated …

A search platform and method for enhancing analysis of contents in a patent/non-patent
literature document by locating/extracting additional similar contents in the patent/non-patent …

US11557276B2 - Ontology integration for document summarization - Google Patents
US11557276B2 - Ontology integration for document summarization - Google Patents Ontology …

Provided is a computer-implemented process including obtaining a corpus of natural-
language text documents, automatically generating questions about information in …

Certain embodiments involve generating summarized versions of video content based on
memorability of the video content. For example, a video summarization system accesses …