Urdu is the national language and lingua franca of Pakistan. It is a grammar enriched language. It has not evolved much in the field of Natural Language Processing (NLP). Urdu language has a big variety of derivation and inflections in a single word. That makes it a challenging language to work on language processing tasks. Research in Natural Language Processing (NLP) and Computational Linguistics (CL) has composed a considerable measure about the history of Urdu language, evolution of Urdu literature, usage of Urdu language in a wide range, effects of other languages on Urdu, Urdu dialect and script etc. Most of the work done on Urdu in the field of Natural Language Processing (NLP) and Computational Linguistics (CL) is related to its morphology, orthography and script. Urdu has a very rich and complex morphology which makes it a challenging language in Natural Language Processing (NLP) and Computational Linguistics (CL) tasks. The purpose of this article is to comprehensively review the morphological and orthographic challenges that arise in Urdu language processing. In modern linguistics morphology and orthography has a central place. Other branches like historical linguistic, phonemics and morphonemics are also important. But this works focuses on Urdu morphology and orthography. Few studies highlighting these Morphological and Orthographic challenges in Urdu Language Processing (ULP) can be found in the literature but still there are many unsolved problems that need to be highlighted and solved. This article presents, groups, and reviews these challenges and also suggests the solution to these challenges.
@InProceedings{FATIMA18.17, author = {Tayyaba Fatima ,Raees Ul Islam and Muhammad Waqas Anwar}, title = {Morphological and Orthographic Challenges in Urdu Language Processing: A Review}, booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {may}, date = {7-12}, location = {Miyazaki, Japan}, editor = {Kiyoaki Shirai}, publisher = {European Language Resources Association (ELRA)}, address = {Paris, France}, isbn = {979-10-95546-24-5}, language = {english} }
Summary of the paper