We present a comprehensive, feature-rich online dictionary for the Sinhala language. Creating digital resources from printed material makes them accessible, easyto-use and allows more features. Sinhala is spoken by over 15 million people, mostly in Sri Lanka. By providing Sinhala language resources in a digital format, Sinhala speakers can make better use of the language, for example, to improve their writing. There was no complete dictionary with Sinhala headwords available on-line. We built a complete on-line Sinhala dictionary and then extended it to support English and Tamil definitions as well. We also built a mobile application and a backend API. Wahara provides real-time suggestions based on the query, search for any morphological form of a word (e.g., past tense), metadata such as part of speech tags and combinations, Trilingual (Sinhala, Tamil, and English) results and spell correction suggestions. It can also process a segment of text and provide definitions of all the words. You can look up words in definitions with a single click. It also has word search history and user-managed favourite word lists. Data was extracted from the Concise Sinhala Dictionary and the Trilingual Dictionary. Due to the richness of features and the completeness of data, Wahara is the most resourceful online dictionary for the Sinhala language.
Keywords: Natural Language Processing | Sinhala | Lexicon |
@phdthesis{iniyage2022advanced,
title={Advanced Interactive Sinhala Dictionary},
author={Iniyage, Isuranga and Mihiranga, Pathum and Wijethunga, Mithun},
year={2022},
abstract={We present a comprehensive, feature-rich online dictionary for the Sinhala language. Creating digital resources from printed material makes them accessible, easyto-use and allows more features. Sinhala is spoken by over 15 million people, mostly in Sri Lanka. By providing Sinhala language resources in a digital format, Sinhala speakers can make better use of the language, for example, to improve their writing. There was no complete dictionary with Sinhala headwords available on-line. We built a complete on-line Sinhala dictionary and then extended it to support English and Tamil definitions as well. We also built a mobile application and a backend API. Wahara provides real-time suggestions based on the query, search for any morphological form of a word (e.g., past tense), metadata such as part of speech tags and combinations, Trilingual (Sinhala, Tamil, and English) results and spell correction suggestions. It can also process a segment of text and provide definitions of all the words. You can look up words in definitions with a single click. It also has word search history and user-managed favourite word lists. Data was extracted from the Concise Sinhala Dictionary and the Trilingual Dictionary. Due to the richness of features and the completeness of data, Wahara is the most resourceful online dictionary for the Sinhala language.},
school={University of Moratuwa},
misc={https://nisansads.staff.uom.lk/Group/pub-details.php?bib=iniyage2022advanced,NLP:SIN,https://goo.gl/iY6aTr},
url={https://nisansads.staff.uom.lk/Group/pub-details.php?bib=iniyage2022advanced}
}
ActivePI: Nisansa de Silva
We propose to build and analyze Sinhala language resources, datasets, and models to strengthen NLP research for this low-resource language, while connecting it to English and Tamil through bilingual lexicons, embeddings, and cross-lingual methods.