Side Project Initiation
Motivation, Planning, and Goals:
Nepali Wiktionary is currently unorganized and small. It would be very time-consuming and ineffective to work alone on this project. Therefore, I started a side project for which I have registered a domain name called nepalinlp.org and it is hosted on the server of my mentor, David De Hilster. With this side project, my goal is to recruit enthusiastic CS, NLP, and linguists in the Nepali language and develop a more organized and structured Wiktionary. I did background research and came up with a word entry template to add unlisted words to Nepali Wiktionary that will give complete information about the very word to the audience which is as follows:
Word | Phonetics/Pronunciation
- Parts of Speech: meaning 1
- Examples of use in sentences
- Parts of Speech: meaning 2..
- Examples of use in sentences
- Synonyms
- synonym 1 , synonym 2, …
- Translation
- English
Using the above format, I will add 20-30 unlisted Nepali words to Wiktionary using NLP++ and HPCC Systems which will act as a template for other enthusiastic people who would be ready to volunteer in this initiative with me. The words will be parsed using NLP++ and will run those analyzers on HPCC Systems. The HPCC Systems and NLP++ & VisualText webpages are linked under “Technology” in the website as well. In this way, I will be able to bring the attention of more people to HPCC Systems and their uses. Simultaneously, I will be able to achieve the project goal by making Nepali Wiktionary ample and in a more structured and useful format.
Words to Add in Wiktionary
I also started to create a dataset where I am adding all the Nepali words that are currently unlisted in the Wiktionary. Some of the words are as follows:
Nepali NLP Initiative 