Abstract
A spellchecker is essential for any language for producing error-free content. While there exist advanced computational tools for Sanskrit, such as word segmenter, morphological analyser, sentential parser, and machine translation, a fully functional spellchecker is not available. This paper presents a Sanskrit spellchecking dictionary for Hunspell, thereby creating a spellchecker that works across the numerous platforms Hunspell supports. The spellchecking rules are created based on the Paninian grammar, and the dictionary design follows the word-and-paradigm model, thus, making it easily extendible for future improvements. The paper also presents an online spellchecking interface for Sanskrit developed mainly for the platforms where Hunspell integration is not available yet.- Anthology ID:
- 2022.icon-main.35
- Volume:
- Proceedings of the 19th International Conference on Natural Language Processing (ICON)
- Month:
- December
- Year:
- 2022
- Address:
- New Delhi, India
- Editors:
- Md. Shad Akhtar, Tanmoy Chakraborty
- Venue:
- ICON
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 290–299
- Language:
- URL:
- https://aclanthology.org/2022.icon-main.35
- DOI:
- Cite (ACL):
- Prasanna S. 2022. Spellchecker for Sanskrit:The Road Less Taken. In Proceedings of the 19th International Conference on Natural Language Processing (ICON), pages 290–299, New Delhi, India. Association for Computational Linguistics.
- Cite (Informal):
- Spellchecker for Sanskrit:The Road Less Taken (S, ICON 2022)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/2022.icon-main.35.pdf