The project is all about Natural Language Processing for the Nepali Language. "Text Summarization" and "Word Segmentation" are implemented in this project.
→ For text summarization, the technique used is TF-IDF.
→ The dataset includes most common words that are used in nepali language. The dataset has various P.O.S. words.
→ The project implements Verbal Inflections.
→ Non-verbal words from the dataset are used as a dictionary to the implemented dictionary based algorithms.
→ Research is done for the verbal part and the most common nepali verbs are categorized into various types. Each type has its own rule of adding of prefixes and suffixes.
→ FSA is implemented for Morphological Recognition.
→ Various Orthographic rules are also taken into consideration while implementing the FSA.
Apart from these regular verbs, two most common irregular verbs are also implemented in the program.