The Fusion of Multilingual Semantic Search and Large Language Models: A New Paradigm for Enhanced Topic Exploration and Contextual Search
Muhammad Mohsin Ather · 2024
Digital news articles are often considered as a primary source of information in today's information-driven society which requires query processing methods to handle the ever-increasing volume of content and various forms of queries. Our goal is to develop a novel approach that can improve the way users access and retrieve news by considering Natural Language Processing (NLP)-driven query processing for news articles. This will address the complexities of news articles written in multiple languages and covering a range of topics. The proposed method helps in enhancing the performance of query processing in applications such as journalism, academic research, and content suggestion. By conducting experiments with Sentence Embeddings, Large Language Model (LLM), and Approximate Nearest Neighbours (ANN), this thesis improves news article search systems. Results show that the method improves the quality of the search results for the queries to return more accurate and relevant search results across different languages.