Summary: This project conducts a comprehensive gap analysis of existing digitization, natural language processing, and knowledge engineering capabilities for Sri Lankan Tamil, followed by the development of targeted NLP tools to address identified limitations. It delivers an end-to-end AI system that ingests, processes, and enriches digitized texts and documents to produce structured, reliable, and trustworthy ...

Summary: The project aims to develop a Retrieval-Augmented Generation (RAG)–based question-answering system using custom, domain-specific English content. The system will retrieve relevant passages from a processed, metadata-enriched text corpus and use them as grounding context for a GPT model to generate accurate and context-aware responses. By combining information retrieval with generative AI, the system is ...

Summary: The content conversion pipeline transforms Noolaham’s digitized documents into structured, machine-readable text. It begins with the ingestion of digital documents such as scanned newspapers, books, magazines, and pamphlets. These documents are first preprocessed to improve quality and consistency. The pipeline then performs layout analysis to identify document structure, followed by article segmentation to separate logical ...