摘要: This paper introduces a two-way Urdu– Roman transliterator based solely on nonprobabilistic finite state transducer that solves the encountered scriptural issues via particular architectural design in combination with set of restrictions. In order to deal enormous amount overgenerations caused by inherent properties Urdu script, depends phonological and orthographic restrictions word list; additionally, default component is implemented allow for unknown entities be transliterated, thus ensuring large degree flexibility addition robustness.
aclweb.org
uni-konstanz.de参考文章(6)
Kenneth R. Beesley, Lauri Karttunen, Finite State Morphology ,(2003)
Annette Hautli, Sebastian Sulger, Tina Bögel, Miriam Butt, Developing a finite-state morphological anlayzer for Urdu and Hindi finite state methods and natural language processing. pp. 86- 96 ,(2007)
Annette Hautli, Sebastian Sulger, Tina Bögel, Miriam Butt, Urdu and the Modular Architecture of ParGram CLT09. ,(2009)
Abbas Malik, Laurent Besacier, Christian Boitet, Pushpak Bhattacharyya, A Hybrid Model for Urdu Hindi Transliteration international joint conference on natural language processing. pp. 177- 185 ,(2009) , 10.3115/1699705.1699746
Sebastian Sulger, Tina Bögel, Tafseer Ahmed, Muhammad Kamran Malik, Miriam Butt, Atif Gulzar, Sarmad Hussain, Ghulam Raza, Transliterating Urdu for a Broad-Coverage Urdu/Hindi LFG Grammar language resources and evaluation. pp. 2921- 2927 ,(2010)
Tejinder Singh Saini, Gurpreet Singh Lehal, A Hindi to Urdu Transliteration System ,(2010)