Analyzing & Enhancing Accuracy of Part of Speech Tagger with the Usage of Mixed Approaches for Gujarati
Pooja M Bhatt1, Amit Ganatra2
1Pooja M Bhatt, Department of Coputer Engineering, CHARUSAT Uniersity, Changa, Gujarat, India.
2Dr. Amit Ganatra, Department of Coputer Engineering, CHARUSAT Uniersity, Changa, Gujarat, India.
Manuscript received on 17 April 2019 | Revised Manuscript received on 23 May 2019 | Manuscript published on 30 May 2019 | PP: 3077-3086 | Volume-8 Issue-1, May 2019 | Retrieval Number: A9254058119/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Tagging an accurate grammar to the specific phrase in sentences could be very crucial undertaking for specific Indian languages. Part of speech tagging is a fundamental manner for one of a kind natural language processing applications like machine translation, speech Recognition etc. Part Of Speech is used for assigning tag the usage of the grammatical statistics of every word of a sentence. We have used statistical approach like Hidden Markov Model (HMM) and rule-based method to investigate the accuracy of a part of speech tagger for Guajarati language. In the paper we discussed available tagging strategies for numerous Indian languages. Further we discussed proposed approached with the use of BIS tag set that includes 11 fundamental tags and more than 25 sub tags. Further we practice HMM model for Sports and amusement information set, we are getting accuracy 70% and 56% respectively. After applying rule based approach we achieved 76% accuracy for sports activities and 80% for Entertainment dataset. After that we have used leisure information set with 95614 phrases and we were given 52% accuracy with hmm and 83 % accuracy with the aid of after making use of rules with hmm.
Index Terms: Hidden Markov Mmodel, Natural Language Processing, Part of Speech Tagging, Statistical Models, Rule Based Approach.
Scope of the Article: Signal and Speech Processing