No Detail Found!

Architecture of Parts of speech Tagger in Sindhi Language

Author(s)
Saira Baby Farooqui Shah Abdul Latif University, Khairpur Sindh Country , Pakistan
Noor Ahmed Shaikh Shah Abdul Latif University, Khairpur Sindh Country , Pakistan
Samina Rajper Shah Abdul Latif University, Khairpur Sindh Country , Pakistan
Abstract
The Sindhi language is intricate and one of the Devangari, Gurmukhi, Landa and Persian Arabic. The script oldest tongue spoken and written in several parts of the of language has many problems like rich morphological world. In this language words segmentation, The short structure, primary and secondary words, white or soft spaces vowel restoration (SV) and parts of Speech (POS) is in words and the same word belongs to many parts of tagging the generally challenging jobs for its natural speeches. Therefore, Tokenization method is used in Sindhi language processing (NLP) applications. Furthermore, corpus to reduce white and soft space. The Tokenization splits it's complex by the features. For example soft spaces in words by which the vowel restoration take place and the lexis, short vowels are compound and complex words are tagger puts tags over words according to the structure of found in Sindhi. For its complexity, Parts of Speech (POS) sentence. Comparing Sindhi language to Arabic, Sindhi has tagging are challenging job for machine learning. It can more vowels and consonants. Each word in Sindhi language help to overcome these ambiguities. Sindhi has eight POS ends with a vowel. These are some rules which describe the according to the formation of sentence. The (POS) change part of speech in the sentence. their nature that human beings easily understand but a computer does not do. To overcome these issues some rules are defined in this model which may help a machine to recognize POS tagging. In POS Architecture has three contrasting phases to resolve the tagging problems in this language and other languages as well. The tokenization is a utensil for NLP for word segmentation (Sentence are break into words, After segmentation of words SVR phase is start for proper vocalization and applied tags for tagging which can help to understand appropriate texts. POS are tagged in the corpus, it removes the uncertainty. The English language has various rules but the Sindhi language identify its functionality by the corpus (vowel, short vowels, space and white spaces). The architecture helps the society to recognize the indigenous structure of language. This architecture also helpful to translator of Sindhi Language, Question Answering, Information Extraction, Machine Text, Summarization, Translation, Sindhi Dictionaries, Information Retrieval and Web Portals.
Publication Details
Page(s) 42-47
DOI DOI not available
Published Journal: Journal of Information & Communication Technology (JICT), Volume: 16, Issue: 2, Year: 2022

Request the full text from PASTIC

Keywords
Natural language processing (NLP), short vowel restoration (SVR), Architecture of Parts of speech tagging
References
M. S. M. H .2021 .Optimal size-performance tradeofs: Weighing pos tagger models,” vol. arXiv preprint arXiv:2104, : 07951.
H. J. L. H. W. Yang .2018 .Dense and tight detection of chinese characters in historical documents: Datasets and a recognition guided detector. , 6 : 30174-30183.
Aliwy A. H. .2013 .Arabic morphosyntactic raw text part of speech tagging system. ”, : .
Sodhar I. N. A. H. J. a. M. I. C. .2019 .Identification of issues and challenges in romanized Sindhi text. no. 9 ), : .
P. P. G. V. P. S. Papageorgiou H . .A Unified POS Tagging Architecture and its Application to Greek. InLREC, : .
Mahar J. A. &. M. G. Q. .2010 .Sindhi part of speech tagging system using wordnet. International Journal of Computer Theory and Engineering, 2(4) : 53.
Mahar J. A. M. G. Q. &. S. H. .2011 .Sindhi diacritics restoration by letter level learning approach. SURJ (Science Series), 43(2) : .
M. U Rahman .2015 .Towards Sindhi Corpus Construction, Linguistics. , 1(1) : 39-48.
M. M. H. Shaikh H. M. J. A. .2017 .Statistical approaches to instant diacritics restoration for sindhi accent prediction. SURJ (Science Series), 49(2) : .
K. C. Webster J. J. . .Tokenization as the initial phase in NLP,”. The 14th International Conference on Computational Linguistics., 4(1992) : .
Attia M. . .. ” Proceedings of the 2007 Workshop on Computational Approaches to Semitic Languages: Common Issues and Resources, : .
.2007 .. , : 65-72.
Schmid L. F.,H L. F.,August L. F. .2008 .Estimation of conditional probabilities with decision trees and an Application to fine-grained pos tagging. Proceedings of the 22nd International Conference on Computational Linguistics (Coling, : 777-784.
Mahar J. A. &. M. G. Q. (. F. .2010 .Rule based part of speech tagging of sindhi language. IEEE, : 101-106.
Hardie A. .2003 .Developing a tag set for automated part-ofspeech tagging in Urdu. In Corpus Linguistics, : .
Hifny Y.,Y. Y. .2012 .Smoothing techniques for Arabic diacritics restoration. (No. 1, : 6-12.
I. S. J. A. S. R. ZITOUNI .2006 .the 44th annual meeting of the Association for Computational Linguistics , no. Association for Computational Linguistics. In Proceedings of the 21st International Conference on Computational Linguistics, : 577-584.
K. R. B. S. P. a. K. D. Singha .2012 .”Part of Speech Tagging in Manipuri: A Rule based Approach. International Journal of Computer, : 51.
0

Citations

0

Downloads

109

Views