MSc DS&AI (Moratuwa), BSc IT (Hons) (Moratuwa)
I am an enthusiastic, self motivated and hard working individual, driven by a passion for delivering excellence in every aspect of the development process. With a sharp attention to detail and a dedication to quality, I excel in dynamic environments where I can contribute innovative solutions, effectively bridging the gap between ideas and implementation. My experience spans building robust RAG chatbot systems using advanced techniques like semantic chunking, hybrid search, and re-ranking, integrating document pipelines with Apache NiFi, and developing scalable data flows with AWS MSK Kafka. I’ve also engineered intuitive web interfaces, backend services, and implemented integrations with platforms like Procore, AWS S3, and ThingsBoard. I enjoy bridging AI, data, and software to create smart, intuitive user experiences driven by creativity and a commitment to excellence.
Keywords: Machine Learning / Deep Learning | Natural Language Processing | Sinhala |
Conference Papers
Lakshani Galwatta, Nisansa de Silva, Sarangi Aththanayake, and Adithya Galwatta, "SalAngaBhava: A Sinhala Market Dataset for Aspect-based Sentiment Analysis", in 2026 Moratuwa Engineering Research Conference (MERCon), 2026, pp. 664-669. doi: 10.1109/MERCon71835.2026.11691353
ActivePI: Nisansa de Silva
We propose to advance aspect-based sentiment analysis (ABSA) by developing enhanced models, datasets, and evaluation methods that improve the accuracy and applicability of sentiment classification across multiple domains.
ActivePI: Nisansa de Silva
We propose to advance natural language processing for low-resource settings by leveraging data augmentation, transfer learning, and model adaptation techniques to overcome the scarcity of annotated data and linguistic resources.
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.
