Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Sanath Jayasena"'
Publikováno v:
CAAI Transactions on Intelligence Technology, Vol 9, Iss 5, Pp 1116-1125 (2024)
Abstract Pre‐trained multilingual language models (PMLMs) such as mBERT and XLM‐R have shown good cross‐lingual transferability. However, they are not specifically trained to capture cross‐lingual signals concerning sentiment words. This pose
Externí odkaz:
https://doaj.org/article/3a7ea0f2b8344079976e08082714330a
Autor:
Kasun Vithanage, Rukshan Wijesinghe, Alex Xavier, Dumindu Tissera, Sanath Jayasena, Subha Fernando
Publikováno v:
PLoS ONE, Vol 18, Iss 12 (2023)
Externí odkaz:
https://doaj.org/article/a93247b0f3ff45ee965217770a87c34c
Publikováno v:
Data Science and Engineering, Vol 4, Iss 3, Pp 223-239 (2019)
Abstract Increasingly organizations are elastically scaling their stream processing applications into the infrastructure as a service clouds. However, state-of-the-art approaches for elastic stream processing do not consider the potential threats of
Externí odkaz:
https://doaj.org/article/07779ccc80094312be97d0dee470ec74
Publikováno v:
2022 IEEE 15th International Conference on Cloud Computing (CLOUD).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::576778ec50d210715a020f8fe990fa1c
https://doi.org/10.1109/cloud55607.2022.00050
https://doi.org/10.1109/cloud55607.2022.00050
Autor:
Budvin Edippuliarachchi, Damika Gamlath, Ruchin Amaratunga, Gunavaran Brihadiswaran, Sanath Jayasena
Publikováno v:
2022 14th International Conference on Bioinformatics and Biomedical Technology.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::664d03e181a54092ffb719b11a020ddf
https://doi.org/10.1145/3543377.3543389
https://doi.org/10.1145/3543377.3543389
Autor:
Alex Xavier, Dumindu Tissera, Rukshan Wijesinghe, Kasun Vithanage, Ranga Rodrigo, Subha Fernando, Sanath Jayasena
Publikováno v:
2021 The 5th International Conference on Advances in Artificial Intelligence (ICAAI).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92775195f54401775d2a4cfc4ee4b74e
https://doi.org/10.1145/3505711.3505715
https://doi.org/10.1145/3505711.3505715
Publikováno v:
2021 Moratuwa Engineering Research Conference (MERCon).
Neural Machine Translation (NMT) tends to perform poorly in low-resource language settings due to the scarcity of parallel data. Instead of relying on inadequate parallel corpora, we can take advantage of monolingual data available in abundance. Trai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::19b433b4af32c322d246da95eb6e0965
https://doi.org/10.1109/mercon52712.2021.9525720
https://doi.org/10.1109/mercon52712.2021.9525720
Publikováno v:
2021 Moratuwa Engineering Research Conference (MERCon).
Bilingual lexicons are an important resource in Natural Language Processing (NLP). Such resources are scarce for Low Resource languages (LRLs) such as Sinhala. However, research on Bilingual Lexical Induction (BLI) on low resource settings is limited
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4351fbf1e02347a0614384fb4ee8a052
https://doi.org/10.1109/mercon52712.2021.9525667
https://doi.org/10.1109/mercon52712.2021.9525667
Publikováno v:
2021 Moratuwa Engineering Research Conference (MERCon).
Neural Machine Translation (NMT) requires a large amount of parallel data to achieve reasonable results. For low resource settings such as Sinhala-English where parallel data is scarce, NMT tends to give sub-optimal results. This is severe when the t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50950803b2b363061d845aa438d4c36a
https://doi.org/10.1109/mercon52712.2021.9525800
https://doi.org/10.1109/mercon52712.2021.9525800
Publikováno v:
2021 13th International Conference on Bioinformatics and Biomedical Technology.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33b76bec63759234534635802913db6d
https://doi.org/10.1145/3473258.3473279
https://doi.org/10.1145/3473258.3473279