公开(公告)号：US20230076773A1

公开(公告)日：2023-03-09

申请号：US17493819

申请日：2021-10-04

Applicant: Microsoft Technology Licensing, LLC

Inventor： Elena POCHERNINA ,  John WINN ,  Matteo VENANZI ,  Ivan KOROSTELEV ,  Pavel MYSHKOV ,  Samuel Alexander WEBSTER ,  Yordan Kirilov ZAYKOV ,  Nikita VORONKOV ,  Dmitriy MEYERZON ,  Marius Alexandru BUNESCU ,  Alexander Armin SPENGLER ,  Vladimir GVOZDEV ,  Thomas P. MINKA ,  Anthony Arnold WIESER ,  Sanil RAJPUT ,  John GUIVER

IPC: G06F40/30 ,  G06F16/901 ,  G06F16/903

Abstract: In various examples there is a computer-implemented method of database construction. The method comprises storing a knowledge graph comprising nodes connected by edges, each node representing a topic. Accessing a topic type hierarchy comprising a plurality of types of topics, the topic type hierarchy having been computed from a corpus of text documents. One or more text documents are accessed and the method involves labelling a plurality of the nodes with one or more labels, each label denoting a topic type from the topic type hierarchy, by, using a deep language model; or for an individual one of the nodes representing a given topic, searching the accessed text documents for matches to at least one template, the template being a sequence of words and containing the given topic and a placeholder for a topic type; and storing the knowledge graph comprising the plurality of labelled nodes.

公开(公告)号：US20230067688A1

公开(公告)日：2023-03-02

申请号：US17460123

申请日：2021-08-27

Applicant: Microsoft Technology Licensing, LLC

Inventor： Elena POCHERNINA ,  John WINN ,  Matteo VENANZI ,  Ivan KOROSTELEV ,  Pavel MYSHKOV ,  Samuel Alexander WEBSTER ,  Yordan Kirilov ZAYKOV ,  Nikita VORONKOV ,  Dmitriy MEYERZON ,  Marius Alexandru BUNESCU ,  Alexander Armin SPENGLER ,  Vladimir GVOZDEV ,  Thomas P. MINKA ,  Anthony Arnold WIESER ,  Sanil RAJPUT

IPC: G06N5/02 ,  G06F40/186

Abstract: In various examples there is a computer-implemented method of database construction. The method comprises storing a knowledge graph comprising nodes connected by edges, each node representing a topic. Accessing a topic type hierarchy comprising a plurality of types of topics, the topic type hierarchy having been computed from a corpus of text documents. One or more text documents are accessed and the method involves labelling a plurality of the nodes with one or more labels, each label denoting a topic type from the topic type hierarchy, by, using a deep language model; or for an individual one of the nodes representing a given topic, searching the accessed text documents for matches to at least one template, the template being a sequence of words and containing the given topic and a placeholder for a topic type; and storing the knowledge graph comprising the plurality of labelled nodes.