Natural language processing knowledge network approach for interactive highlighting and summary

Alexander Dudko, Tatiana Endrjukaite, Yasushi Kiyoki

研究成果: Chapter

抄録

This paper describes a new approach of data retrieval from free text documents in medical domain. Proposed approach creates the document summary and highlights most important keywords in the text by means of document ontology, as an internal representation of the document. This document ontology is a graph with concepts, relations between them, and concept points as a metric of relevance. By means of points the approach performs ambiguity resolution, selects most relevant concepts to display in the summary, and votes for keywords highlighting in the text. Moreover, interactive highlighting reveals additional information from document ontology as reader interacts with the keywords and summary in the document. The described approach helps to speed up analysis and decision-making processes by means of providing aggregated summary for a document and highlighting most meaningful parts of the text.

本文言語English
ホスト出版物のタイトルLecture Notes in Networks and Systems
出版社Springer
ページ191-200
ページ数10
DOI
出版ステータスPublished - 2019

出版物シリーズ

名前Lecture Notes in Networks and Systems
68
ISSN(印刷版)2367-3370
ISSN(電子版)2367-3389

ASJC Scopus subject areas

  • 制御およびシステム工学
  • 信号処理
  • コンピュータ ネットワークおよび通信

フィンガープリント

「Natural language processing knowledge network approach for interactive highlighting and summary」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル