Rule-Based Named Entity Recognition in Urdu

Named Entity Recognition or Extraction (NER) is an important task for automated text processing for industries and academia engaged in the field of language processing, intelligence gathering and Bioinformatics. In this paper we discuss the general problem of Named Entity Recognition, more specifically the challenges in NER in languages that do not have language resources e.g. large annotated corpora. We specifically address the challenges for Urdu NER and differentiate it from other South Asian (Indic) languages. We discuss the differences between Hindi and Urdu and conclude that the NER computational models for Hindi cannot be applied to Urdu. A rule-based Urdu NER algorithm is presented that outperforms the models that use statistical learning.