Challenges of Urdu Named Entity Recognition: A Scarce Resourced Language

Saeeda Naz ； Arif Iqbal Umar ； Syed Hamad Shirazi ； Sajjad Ahmad Khan ； Imtiaz Ahmed ； Akbar Ali Khan

《Research Journal of Applied Sciences, Engineering and Technology》 8卷10期 (2014/09) Pp. 1272-1278

並列摘要

In this study, we present a brief overview of Named Entity Recognition (NER) system, various approaches followed for NER systems and finally NER systems for Urdu language. Urdu language raises several challenges to Natural Language Processing (NLP) largely due to its rich morphology. Research against NER systems in Urdu language is at infancy stage therefore the focus of this study is on challenges and peculiarities of Urdu NER system. In this study we also explore the previous work done on NER systems for South and South East Asian Languages (SSEAL). Finally, we conclude the existing work in Urdu NER which is a scarce resourced and morphologically rich language and other SSEAL which have similar features to Urdu language.

並列關鍵字

CRF ； ME ； SSEAL ； Urdu named entity recognition