Tool: Relation Extractor
Date
2021-10-15
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Boğaziçi University
Contact Person
Abdullatif, Köksal, dip@boun.edu.tr, Boğaziçi University
Abstract
Description
Relation extraction is the process of determining the relation between entities in a sentence. Given a sentence with two entities marked with special symbols, the relation extractor outputs either the name of the relation that holds between these entities or the phrase “no_relation” if no relation can be determined. The tool supports five languages (English, French, German, Spanish, Turkish) and 18 directional relations (per:alternate names, per:origin, per:spouse, per:title, per:employee of, per:countries of residence, per:stateorprovinces of residence, per:cities of residence, per:country of birth, org:alternate names, org:subsidiaries, org:top members/employees, org:founded, org:founded by, org:country of headquarters, org:stateorprovince of headquarters, org:city of headquarters, org:members) and a no relation class, which results in 37 different classes.
Keywords
relation, extraction
Citation
Referenced by
Sponsor
TÜBİTAK, 2211-A, BİDEB, nationalFunds