no code implementations • EACL (DravidianLangTech) 2021 • Anosha Ignatius, Uthayasanker Thayasivam
Speech carries not only the semantic content but also the paralinguistic information which captures the speaking style.
no code implementations • EACL (DravidianLangTech) 2021 • Charangan Vasantharajan, Uthayasanker Thayasivam
Code-Mixed Offensive contents are used pervasively in social media posts in the last few years.
no code implementations • 23 May 2023 • Thejan Wijesinghe, Chamath Abeysinghe, Chanuka Wijayakoon, Lahiru Jayathilake, Uthayasanker Thayasivam
We develop an automated video colorization framework that minimizes the flickering of colors across frames.
no code implementations • 17 Feb 2022 • Ravinga Perera, Thilakshi Fonseka, Rashmini Naranpanawa, Uthayasanker Thayasivam
The performance of Neural Machine Translation (NMT) depends significantly on the size of the available parallel corpus.
1 code implementation • 13 Sep 2021 • Charangan Vasantharajan, Laksika Tharmalingam, Uthayasanker Thayasivam
Since Tamil and Sinhala are Low-Resource Languages, we improved the performance of Tesseract by employing LSTM-based training on more than 20 legacy fonts to recognize printed characters in these languages.
1 code implementation • 24 Aug 2021 • Charangan Vasantharajan, Uthayasanker Thayasivam
The experimental results showed that ULMFiT is the best model for this task.
no code implementations • 6 Apr 2021 • Haritha Jayasinghe, Tarindu Jayatilaka, Ravin Gunawardena, Uthayasanker Thayasivam
Thus, a need arises for a simulated environment where they can predict users' reactions to changes in the platform-specific parameters such as trip fares and incentives.
no code implementations • 10 Dec 2020 • Yasas Senarath, Uthayasanker Thayasivam
In this paper, we present an experiment on using deep learning and transfer learning techniques for emotion analysis in tweets and suggest a method to interpret our deep learning models.
no code implementations • LREC 2020 • Prasadi Abeywardana, Uthayasanker Thayasivam
The next hype of data experimentation is going to be heavily dependent on privacy preserving techniques mainly as it{'}s going to be a legal responsibility rather than a mere social responsibility.
no code implementations • ACL 2019 • Yohan Karunanayake, Uthayasanker Thayasivam, Surangika Ranathunga
Current state-of-the-art speech-based user interfaces use data intense methodologies to recognize free-form speech commands.
no code implementations • 12 Jun 2019 • Nadeesha Pathirana, Sandaru Seneviratne, Rangika Samarawickrama, Shane Wolff, Charith Chitraranjan, Uthayasanker Thayasivam, Tharindu Ranasinghe
Concept identification is a crucial step in understanding and building a knowledge base for any particular domain.
1 code implementation • WS 2018 • Yasas Senarath, Uthayasanker Thayasivam
This paper describes an approach to solve implicit emotion classification with the use of pre-trained word embedding models to train multiple neural networks.