To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Parts of Speech Tagging of Romanized Sindhi Text by applying Rule Based Model |
|
Author |
Irum Naz Sodhar, Akhtar Hussain Jalbani, Muhammad Ibrahim Channa and Dil Nawaz Hakro |
| Citation |
Vol. 19 No. 11 pp. 91-96 |
|
Abstract |
Role of natural language processing (NLP) in machine learning is very important and its task’s such as Parts?of?Speech (POS) tagging, tokenization of (words, sentences, paragraph) etc. Parts-of-speech tagging performed as a pre-processing steps in natural language processing, such as syntactic parsing, information extraction (IE) and machine translation (MT). The Romanized Sindhi lexicon for computational processing is not available. In this research work of POS tagging of Romanized Sindhi text based on online Python tool were used and performed the task of POS tagging. By applying rule based model for analyzing the text and extract the text from given input text. POS Tagging algorithms were also designed for implementation of Romanized Sindhi Text (RST). Construction of RST data of 100 sentences and these sentences are depends on the (Noun-Verb-Determinant) for POS tagging and have important task towards computational RST processing. The rule based model was used for the POS tagging of RST and it worked in easiest way generate appropriate results of RST. This result will promote the need for further research to perform different task in different domain. |
|
Keywords |
Natural language processing (NLP), Parts-of-speech (POS), Romanized Sindhi Text (RST), Algorithm, Python. |
|
URL |
