mithash42-ux/Kikuyu-Named-Entity-framework

A memory-based framework for named entity recognition Explosion of unstructured information demands advanced extraction techniques.(Mikhailov&shivlina 2020) Named Entity Recognition (NER) is a subfield of NLP: Identifies entities (person, location, organization, etc.). Li, Sun, Han, and Li, 2020) Challenges in low-resource languages: Lack of annotated corpora and NLP tools. Memory Based Learning (MBL): Stores training instances for comparison with new input. (Ouchi, et. Al,2020) The exponential growth of published information presents significant challenges in managing and extracting meaningful insights from unstructured data. Named Entity Recognition (NER) plays a critical role in transforming such data into structured, machine-readable formats by identifying and categorizing named entities into predefined semantic classes. This study aimed to develop and evaluate a memory-based NER framework tailored for Kikuyu, a low-resource Bantu language. Leveraging the TiMBL (Tilburg Memory-Based Learner) algorithm, implementing KNN with k=1, the research implemented a k-nearest neighbor approach to classify entities based on manually annotated data from the Kikuyu Bible corpus. The methodology incorporated quality control measures such as inter-annotator agreement and cross-validation to ensure reliability. Experimental results demonstrated promising performance, achieving 72.54% Precision, 72.67% Recall, and a 72.5% F-score. These findings underscore the viability of memory-based learning for NER in resource-scarce languages and contribute a novel annotated Kikuyu corpus and framework for future linguistic and NLP applications.