Browsing by Author "Thayasivam, U"

Sort by: Order: Results:

  • ACTSEA : annotated corpus for Tamil & Sinhala emotion analysis 
    Jenarthanan, R; Senarath, Y; Thayasivam, U [Conference-Abstract]
    The purpose of text emotion analysis is to detect and recognize the classification of feeling expressed in text. In recent years, there has been an increase in text emotion analysis studies for English language since ...
  • Application of noise filter mechanism for t5-based text-to-sql generation 
    Aadhil Rushdy, MR; Thayasivam, U [Conference-Full-text]
    The objective of the text-to-SQL task is to convert natural language queries into SQL queries. However, the presence of extensive text-to-SQL datasets across multiple domains, such as Spider, introduces the challenge ...
  • A deep learning ensemble hate speech detection approach for sinhala tweets 
    Munasinghe, S; Thayasivam, U [Conference-Full-text]
    We live in an era where social media platforms play a key role in society. These platforms support most of the native languages and this has enabled people to express their opinions conveniently. Also, it is very common ...
  • Domain specific named entity recognition in tamil 
    Murugathas, R; Thayasivam, U [Conference-Full-text]
    This paper presents a domain specific Tamil Named Entity Recognizer for history domain. The system uses a manually annotated corpus of 23k tokens and the dataset is tagged with 36 tags related to history domain. NER model ...
  • End To End Model For Speaker Identification With Minimal Training Data 
    Balakrishnan, S; Jathusan, K; Thayasivam, U [Conference-Full-text]
    Deep learning has achieved immense universality by outperforming GMM and i-vectors on speaker identification. Neural Network approaches have obtained promising results when fed by raw speech samples directly. Modified ...
  • Hybrid approach for accurate and interpretable representation learning of knowledge graph 
    Yogendran, N; Kanagarajah, A; Chandiran, K; Thayasivam, U [Conference-Full-text]
    Representation learning of knowledge graph aims to embed both entities and relations into a low-dimensional space. However, there are still some gaps in the knowledge graph embedding methods in providing interpretation of ...
  • Language model-based spell-checker for Sri Lankan names and addresses 
    Udagedara, Y; Elikewela, B; Thayasivam, U [Conference-Full-text]
    Names are used abundantly in various applications, but traditional spell-checkers are not adapted to correcting errors in names. In this research, we suggest a spell-checker for Sri Lankan names and addresses. The main ...
  • Low resource multi-asr speech command recognition 
    Mohamed, I; Thayasivam, U [Conference-Full-text]
    There are several applications when comes to spoken language understanding (SLU) such as topic identification and intent detection. One of the primary underlying components used in SLU studies are ASR (Automatic Speech ...
  • Shadow removal for documents with reflective textured surface 
    Ravindran, A; Arudselvam, U; Thayasivam, U [Conference-Full-text]
    An increasing number of institutions are converting from traditional verification to online digital verification of user documents. In Sri Lanka, this requires clean digital images of documents such as the National Identity ...
  • Speech command recognition using self-supervised asr in Tamil 
    Tharmakulasingham, I; Thayasivam, U [Conference-Full-text]
    ASR technology has made significant advancements, approaching performance levels comparable to humans. However, developing ASR models for all languages, especially Low Resource Languages (LRLs), presents challenges due ...
  • Taxi trip travel time prediction with isolated XGBoost regression 
    Kankanamge, KD; Witharanage, YR; Withanage, CS; Hansini, M; Lakmal, D; Thayasivam, U [Conference-Abstract]
    Travel time prediction is crucial in developing mobility on demand systems and traveller information systems. Precise estimation of travel time supports the decision-making process for riders and drivers who use such ...
  • Video colorization dataset and benchmark 
    Abeysinghe, C; Wijesinghe, T; Wijesinghe, C; Jayathilake, L; Thayasivam, U [Conference-Abstract]
    Video colorization is the process of assigning realistic, plausible colors to a grayscale video. Compared to its peer, image colorization, video colorization is a relatively unexplored area in computer vision. Most of ...