Abstract
Background: A grammar checker can be used as a proof reading tool, which depends upon the basic definition of the words. If words are not defined correctly or are not being tagged with correct grammatical meaning, the results will not be accurate. Objective: To attain this accuracy, Morphological analyser plays a crucial role. In Hindi, as the whole structure and meaning of a sentence depends upon a Noun, so it is mandatory to tag a Noun word properly. But, to tag a Noun with its correct grammatical meaning is a challenging chore. Methods: To tag a word, the word is being input in the tool, which is firstly searched inside the dictionary. If the word is not found in the dictionary, then the grammar rules are applied to analyse the word. As noun, contains names also, so some times the rules are not possible to apply on the words. In that scenario, words are manually tagged and then added to dictionary for further use. Grammar tag set of 650 tags is used to generate more accurate results. All the words are stored in a database. The performance is measured by using Precision and Recall. Furthermore, this technique can be extended to define other categories of grammar like verb, adjective, adverb, etc. Results: This paper represents a method for a Rule-Based Morphological Analyser for Hindi Nouns only. It utilizes-a dictionary and a rule-based approach for defining words with their grammatical meanings using the morphological analyser. The designed morph which has been discussed in this work stores all the words in a database. As this morph analyser uses a set of 650 plus grammatical tag sets (for complete Hindi morphological analyser), the user will always get more accurate results. The Authors have preferred both time and accuracy over memory space, which is not a big issue these days. Therefore this approach can be used for both types of morphological approach. Conclusion: Furthermore, this method can be extended to the other categories of the Hindi Grammar like Adverbs, Adjectives, and Verbs, etc. The results are very promising and are expected to provide even more advancement to the existing strategies and methodologies.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Recent Advances in Computer Science and Communications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
