Evaluation for POS tagger, chunk and resolving issues in word sense disambiguate in machine translation for Hindi to English languages
Shachi Mall, Umesh Chandra Jaiswal · International Conference on Computing for Sustainable Global Development · 2016
Our paper develops innovative algorithms for machine translation system based on the innovative algorithms for parts of speech tagger, chunking, word sense disambiguate and word translation in English. Parts of speech tagging and chunking for 1657 tokens with 990 phrases for Hindi languages and to calculate the accuracy we created confusion matrix an evaluate Precision, Recall, F-score, Accuracy for chunk accuracy: 81.23%; precision: 66.57%; recall: 73.03%; F-score: 69.65, 90.31, POS accuracy: 94.75%; precision: 90.67%; recall: 93.23%; F-score 91.93. Rule based and learning algorithm (Conditional Random Fields) is used to develop the system.