Researchers at the Indian Institute of Technology, Roorkee have developed an efficient method for Sanskrit text sentiment analysis. The proposed technique has achieved 87.50 per cent accuracy for machine translation and 92.83 per cent accuracy for sentiment classification.
These methods were not explored to its full potential because of the unavailability of sufficient labeled data. The research proposed a method that comprises models for machine translation, translation evaluation, and sentiment analysis.
The machine translations have been used as cross-lingual mapping of the source and the target language. The obtained English translations are sufficiently mature and natural as the original English sentences.
The dataset to perform this research was taken from the Valmiki Ramayana website which has been developed and maintained by the researchers of IIT Kanpur. The researchers plan to explore the morphological properties of Sanskrit for better classification using only root words and their respective suffixes and prefixes.
They are also planning to evaluate whether the morphological richness of Sanskrit is retained while translating it to English. And, they also plan to obtain a model that discerns the context of words in multiple languages and provides word embeddings of lesser dimensions. The model has been published as a research paper in the journal, ‘Applied Intelligence’.