Extraction of the Triggering Causes of a Query Event

Datta, Srijon (2023) Extraction of the Triggering Causes of a Query Event. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (5MB) | Preview

Abstract

The main goal of traditional information retrieval systems is to find documents that are pertinent to a certain query idea. But when working with sources like collections of news articles, a user may frequently want to find documents that explain the series of circumstances that may have led to the news event in addition to those that describe the news event itself. Because they involve several underlying causative components, these interactions may be intricate. In response to this demand from the issue, we create the aim of causal information extraction. This work uses a Convolutional Neural Network (CNN) and a Transformer-based model to give an in-depth structure for causality-driven document classification. The overall architecture includes phases for gathering data, extracting information from documents, indexing, and creating input vectors for models. Regarding causal queries, the suggested models successfully separate relevant and irrelevant content. The Transformer-based BERT model outperforms all others in experimental assessment, effectively predicting document relevance with nearly 72% accuracy rate. The work demonstrates the potential of data-driven models in addressing difficult information retrieval problems and identifies prospective directions for model optimization and dataset augmentation in the future.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Milosavljevic, Vladimir UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Electronic computers. Computer science > Computer Systems > Information Storage and Retrieval Systems T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science > Computer Systems > Information Storage and Retrieval Systems
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	08 Nov 2024 13:32
Last Modified:	08 Nov 2024 13:32
URI:	https://norma.ncirl.ie/id/eprint/7177

Actions (login required)

View Item