Skip to content

Latest commit

 

History

History
2 lines (2 loc) · 1.18 KB

File metadata and controls

2 lines (2 loc) · 1.18 KB

Sanskrit, recognized as one of the most ancient languages known to mankind, holds a significant position in history due to its extensive influence on a wide range of Indo-European languages. The profound impact of Sanskrit can be observed in the linguistic development and evolution of numer-ous languages that fall under the Indo-European language family. I found this topic interesting to approach because it has a highly systematic and regular grammar with precise rules for word formation, syntax, and phonetics, also because it holds a wide range of words and expressions, some of these represents specialized terms for various domains such as philosophy, mathematics, astronomy, medicine, and literature. The primary objective of this paper was to analyze a dataset that consists of translated texts from Sanskrit to English, also to use a pre-trained model. An improvement that could be considered in future iterations is to perform a more extensive preprocessing of the English data by removing punctuation marks. This is because these punctuation marks were still present in the dataset and could potentially impact the translation accuracy. By applying a thorough preprocessing step to eliminate