1 code implementation • 24 Apr 2023 • Yudhanjaya Wijeratne, Ishan Marikar
Low-rank adaptation (LoRA) and question-answer datasets from large language models have made it much easier for much smaller models to be finetuned to the point where they display sophisticated conversational abilities.
no code implementations • 26 Oct 2022 • Gihan Weeraprameshwara, Vihanga Jayawickrama, Nisansa de Silva, Yudhanjaya Wijeratne
In the process of numerically modeling natural languages, developing language embeddings is a vital step.
no code implementations • 11 Jan 2022 • Gihan Weeraprameshwara, Vihanga Jayawickrama, Nisansa de Silva, Yudhanjaya Wijeratne
The relationship between Facebook posts and the corresponding reaction feature is an interesting subject to explore and understand.
no code implementations • 1 Dec 2021 • Vihanga Jayawickrama, Gihan Weeraprameshwara, Nisansa de Silva, Yudhanjaya Wijeratne
This paper uses millions of such reactions, derived from a decade worth of Facebook post data centred around a Sri Lankan context, to model an eye of the beholder approach to sentiment detection for online Sinhala textual content.
1 code implementation • 15 Jul 2020 • Yudhanjaya Wijeratne, Nisansa de Silva
This paper presents two colloquial Sinhala language corpora from the language efforts of the Data, Analysis and Policy team of LIRNEasia, as well as a list of algorithmically derived stopwords.