Tagging Efficiency Analysis on Part of Speech Taggers
Ritu Banga, Pulkit Mehndiratta · 2017
We have conducted empirical tests on the different NLTK Part of Speech taggers. Corpora from different users on Twitter has been collected and used for the evaluation for the purpose of these taggers. These taggers are used for experimentation on different data size and their results have been compared on the basis of their accuracy and total time taken for training and testing the dataset. Based on the results, we have selected the best tagger among all the taggers for tagging short messages such as tweets whose length is confined to 140 characters. Some of the taggers yield good results in terms of accuracy and some taggers perform well in terms of computation and time.