KIT | KIT-Bibliothek | Impressum | Datenschutz

Towards Entity Correctness, Completeness and Emergence for Entity Recognition

Zhang, Lei; Dong, Yunpeng; Rettinger, Achim

Abstract:
Linking words or phrases in unstructured text to entities in knowledge bases is the problem of entity recognition and disambiguation. In this paper, we focus on the task of entity recognition in Web text to address the challenges of entity correctness, completeness and emergence that existing approaches mainly suffer from. Experimental results show that our approach significantly outperforms the state-of-the-art approaches in terms of precision, F-measure, micro-accuracy and macro-accuracy, while still preserving high recall.



Originalveröffentlichung
DOI: 10.1145/2740908.2742766
Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Publikationstyp Proceedingsbeitrag
Jahr 2015
Sprache Englisch
Identifikator ISBN: 978-1-4503-3473-0
KITopen-ID: 1000050004
Erschienen in WWW '15 Companion. 24th International Conference on World Wide Web, Florence, Italy, May 18 - 22, 2015. Ed.: A. Gangemi
Verlag ACM, New York (NY)
Seiten 143-144
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page