Survey on Parts of Speech Tagging for Gujarati

Abstract

The study describes the survey on Part of Speech tagging using different approaches for various Indian languages. Indian languages have rich morphological effect, so it may create many problems while tagging the sentences. Researchers have done work on POS tagging for various languages like Hindi, Marathi, Panjabi, English etc. With over 60 million users worldwide, Gujarati is an Indian language that currently has numerous initiatives in place for the development of natural language processing (NLP) resources and applications for Indian languages. It has been demonstrated that the efficacy of translation can be enhanced through the utilization of part-of-speech tagging and stemming-assisted transliteration. It has also been noted that a considerable amount of the material in Gujarati undergoes transliteration during the translation process into the Hindi language. They have used different tagging approaches like statistical, rule based etc. POS Tagging is the basic step for NLP; for that, different tagsets are required that are discussed in this survey.