Systems and methods for automatically generating content summaries for topics

A technique for automatically generating, summarizing content, applied in the field of fragmentation and definition of concepts, to solve problems such as unmet requirements

Active Publication Date: 2020-03-17
ELSEVIER
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these sources do not satisfy the need for authoritative information on concepts

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Systems and methods for automatically generating content summaries for topics
  • Systems and methods for automatically generating content summaries for topics
  • Systems and methods for automatically generating content summaries for topics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] Embodiments of the present disclosure relate to computer-based systems and methods that scan entire text documents, extract relevant and targeted pieces of textual information about a particular concept from the text, and identify the most relevant pieces of textual information for the particular concept.

[0016] Embodiments of the present disclosure include systems and methods for consuming unstructured text. For example, the systems and methods consume entire book chapters in the form of XML text. As will be described in more detail herein, the system generates annotated data as output on unstructured text. For example, the systems and methods may utilize one or more annotation algorithms that recognize named entities in unstructured text (eg, gazetteers or named entity recognizers). The annotated data contains metadata representing term annotations for various terms found in the text as well as marking the start and end offsets of concepts within sections of the un...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A method of automatically generating content summaries for topics includes receiving a taxonomy for a concept and a text corpus. The method further includes generating an annotated dataset having termannotations corresponding to the concept from the text corpus based on the taxonomy, parsing the annotated dataset into a custom generated document object having a structured layout, determining features for the term annotations, and extracting snippets from the custom generated document object, where each of the snippets corresponds to a section of the custom generated document object. The method further includes scoring the snippets based on the features such that each of the snippets corresponds to a score, filtering one or more snippets from the snippets when one or more snippet filteringconditions is met, ranking the snippets into an ordered list for the concept based on the score, and providing, to a user computing device, the ordered list.

Description

[0001] Cross References to Related Applications [0002] This application claims the benefit of U.S. Provisional Application No. 62 / 520,991, filed June 16, 2017, the contents of which are hereby incorporated by reference in their entirety. technical field [0003] The present description generally relates to systems and methods for automatically generating subject content summaries, and more specifically, systems and methods for extracting snippets and definitions of concepts within a text corpus corresponding to content summaries. Background technique [0004] As the volume and density of electronic content increases, researchers, authors, professors, students, etc. face the increasing challenge of searching, dissecting, and identifying quality primary references relevant to their respective fields of interest. Currently, many people utilize publicly available searchable content, such as Wikipedia, to obtain additional information on concepts. However, these sources do not...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/335G06F16/33G06F16/34G06F16/9535G06F16/93
CPCG06F16/345G06F16/93G06F16/334G06F16/335G06F16/9535
Inventor 马吕斯·多恩巴尔斯里尼瓦桑·萨提亚·萨米尔·库马尔·希武库拉贾德森·邓纳姆瑞克·米斯拉米歇尔·格雷戈里
Owner ELSEVIER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products