Designing the Neural Model for POS Tag Classification and Prediction of Words from Ancient Stone Inscription Script
S. Ezhilarasi, Dr.P.Uma Maheswari · Int. J. of Aquatic Science · 2021
POS (Part-of-Speech) Tagging is essential to indicate labeling the words in thecorpus into grammatical categories in text analysis and marking up linguistic words in atext. According to the inflections and combinations in the words of Tamil language, thereis still difficulty in POS Tagging classification and prediction of Tags of the words as theautomated tools are very rare compared to the aspects of rich English language. As if thereare tools for modern Tamil language there is a lack of such statistical methods andtechniques for the Ancient Tamil language such as the texts from inscriptions and scriptsof stone where the words are lengthy and combined without splitting up into morphemes orlemmas. Package supportiveness and availability also considerably have some issues indealing with it as the words of Ancient Tamil script differs from modern Tamil. Theproposed work overcomes the complexity of classifying ancient words. The proposed workis based on designing the Neural Model for POS Tag Classification and Prediction ofWords from the Ancient 11th century stone inscription script. Bi-LSTM model isimplemented with the embedding layer of vectors of words for training the POS Taggingmodel based on pattern generation of regular expressions and classifying the words intotags and prediction of Tags of words for any novel script given that involves syntactic tagassigning and predicting tag for concerning words efficiently. The proposed modelprovides 88.88% accuracy compared to the existing works in the stream.