Multilingual Entity Matching

12 Pages Posted: 8 Jan 2019 Last revised: 13 Jul 2020

See all articles by Ilgiz Mustafin

Ilgiz Mustafin

Innopolis University

Marius Frunza

University Paris Dauphine

Jooyoung Lee

Innopolis University

Date Written: December 25, 2018

Abstract

The aim of this paper is to explore methods of multilingual entity matching. Name matching is currently the main technique used for entity resolution. When dealing with entities having features recorded in different languages and with different alphabets the basic approaches have serious limitation. The basic name matching approach using string comparison metrics is enriched with phonetic rules and with relational information. The results show that the approach using transliteration enhanced by phonetic matching provides with the best performance.

Keywords: entity resolution, multilingual entity matching, transliteration

JEL Classification: C80

Suggested Citation

Mustafin, Ilgiz and Frunza, Marius and Lee, Jooyoung, Multilingual Entity Matching (December 25, 2018). Available at SSRN: https://ssrn.com/abstract=3306378 or http://dx.doi.org/10.2139/ssrn.3306378

Ilgiz Mustafin

Innopolis University

Innopolis, Republic of Tatarstan
Russia

Marius Frunza (Contact Author)

University Paris Dauphine ( email )

Place du Maréchal de Lattre de Tassigny - 75775 PA
Paris, 75775
France

Jooyoung Lee

Innopolis University ( email )

Innopolis, Kazan
Russia

HOME PAGE: http://https://university.innopolis.ru/en/

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
212
Abstract Views
832
Rank
260,572
PlumX Metrics