Text segmentation using light syntax parsing and fuzzy systems

Omar Ali*, Alexander Gegov, Ella Haig, Rinat Khusainov

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present our positions and proposition in regards to the process of text segmentation. The method discussed below aims to improve upon the current processes available for text segmentation by introducing the concept of fuzzy boundaries. our method of segmenting text concerns a population of boundaries to be in a fuzzy state whereby the decision of boundary insertion is determined by a fuzzy system with syntactic information serving as the inputs. Furthermore, we aim to build on this method in the future with the goal of presenting a multifaceted segmentation approach that is applicable across various domains that require segmentation: Text summarisation, Rhetorical structure theory, sentence-based segmentation and paragraph-based segmentation.

Original languageEnglish
Title of host publicationIntelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation - Proceedings of the INFUS 2021 Conference
EditorsCengiz Kahraman, Selcuk Cebi, Sezi Cevik Onar, Basar Oztaysi, A. Cagri Tolga, Irem Ucal Sari
PublisherSpringer
Pages36-43
Number of pages8
ISBN (Electronic)9783030856267
ISBN (Print)9783030856250
DOIs
Publication statusPublished - 24 Aug 2021
EventInternational Conference on Intelligent and Fuzzy Systems - Istanbul, Turkey
Duration: 24 Aug 202126 Aug 2021

Publication series

NameLecture Notes in Networks and Systems
Volume307
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceInternational Conference on Intelligent and Fuzzy Systems
Abbreviated titleINFUS 2021
Country/TerritoryTurkey
CityIstanbul
Period24/08/2126/08/21

Keywords

  • fuzzy systems
  • text pre-processing
  • text segmentation

Fingerprint

Dive into the research topics of 'Text segmentation using light syntax parsing and fuzzy systems'. Together they form a unique fingerprint.

Cite this