Unsupervised text segmentation by topic

Adi Shalev; Yair Horesh; Yehezkel Shraga Resheff; Oren Sar Shalom; Alexander Zhicharevich

Unsupervised text segmentation by topic

Adi Shalev (Inventor)
, Yair Horesh (Inventor)
, Yehezkel Shraga Resheff (Inventor)
, Oren Sar Shalom (Inventor)
, Alexander Zhicharevich (Inventor)

BA Business Department

Research output: Patent

Abstract

A processor may generate a plurality of vectors from an original text by processing the original text with at least one unsupervised learning algorithm. Each of the plurality of vectors may correspond to a separate portion of a plurality of portions of the original text. The processor may determine respective segments to which respective vectors belong. The processor may minimize a distance between at least one vector belonging to the segment and a known vector from among one or more known vectors and applying a label of the known vector to the segment.

Original language	English
Patent number	US10984193
IPC	G06N 20/ 10 A I
Priority date	8/01/20
State	Published - 20 Apr 2021

Cite this

@misc{3b63b88caabb4adca2657f6d4e9c0556,

title = "Unsupervised text segmentation by topic",

abstract = "A processor may generate a plurality of vectors from an original text by processing the original text with at least one unsupervised learning algorithm. Each of the plurality of vectors may correspond to a separate portion of a plurality of portions of the original text. The processor may determine respective segments to which respective vectors belong. The processor may minimize a distance between at least one vector belonging to the segment and a known vector from among one or more known vectors and applying a label of the known vector to the segment.",

author = "Adi Shalev and Yair Horesh and Resheff, \{Yehezkel Shraga\} and Shalom, \{Oren Sar\} and Alexander Zhicharevich",

year = "2021",

month = apr,

day = "20",

language = "אנגלית",

type = "Patent",

note = "US10984193; G06N 20/ 10 A I",

}

TY - PAT

T1 - Unsupervised text segmentation by topic

AU - Shalev, Adi

AU - Horesh, Yair

AU - Resheff, Yehezkel Shraga

AU - Shalom, Oren Sar

AU - Zhicharevich, Alexander

PY - 2021/4/20

Y1 - 2021/4/20

N2 - A processor may generate a plurality of vectors from an original text by processing the original text with at least one unsupervised learning algorithm. Each of the plurality of vectors may correspond to a separate portion of a plurality of portions of the original text. The processor may determine respective segments to which respective vectors belong. The processor may minimize a distance between at least one vector belonging to the segment and a known vector from among one or more known vectors and applying a label of the known vector to the segment.

AB - A processor may generate a plurality of vectors from an original text by processing the original text with at least one unsupervised learning algorithm. Each of the plurality of vectors may correspond to a separate portion of a plurality of portions of the original text. The processor may determine respective segments to which respective vectors belong. The processor may minimize a distance between at least one vector belonging to the segment and a known vector from among one or more known vectors and applying a label of the known vector to the segment.

M3 - ???researchoutput.researchoutputtypes.patent.patent???

M1 - US10984193

ER -

Unsupervised text segmentation by topic

Abstract

Fingerprint

Cite this