Skip to main navigation Skip to search Skip to main content

Real-time entity resolution by multiple indices

  • Hebei University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Entity resolution (ER) is the process of extracting and matching records/tuples from one or more datasets that refer to the same real-world entity and merging the matching records into a tuple or a cluster. In this paper, we primarily focus on ER for datasets with text attributes. By creating different local indices on individual attributes and constructing the corresponding algorithm and ranking function for indices, we present an approach to resolve records involving duplicates, misspellings, or NULL text attributes for a dirty dataset. Extensive experiments are conducted to demonstrate the performances of our proposed approach.

Original languageEnglish
Title of host publication14th International Conference on Computer Science and Education, ICCSE 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1063-1068
Number of pages6
ISBN (Electronic)9781728118444
DOIs
StatePublished - Aug 2019
Event14th International Conference on Computer Science and Education, ICCSE 2019 - Toronto, Canada
Duration: Aug 19 2019Aug 21 2019

Publication series

Name14th International Conference on Computer Science and Education, ICCSE 2019

Conference

Conference14th International Conference on Computer Science and Education, ICCSE 2019
Country/TerritoryCanada
CityToronto
Period08/19/1908/21/19

Keywords

  • Dirty dataset
  • Entity resolution
  • Multiple indices
  • Ranking function
  • Text attribute

Fingerprint

Dive into the research topics of 'Real-time entity resolution by multiple indices'. Together they form a unique fingerprint.

Cite this