Enhanced named entity recognition algorithm for Filipino cultural and heritage texts
1 Bachelor of Science in Computer Science, College of Information Systems and Technology Management, Pamantasan Ng Lungsod Ng Maynila, Philippines.
2 College of Information Systems and Technology Management, Pamantasan Ng Lungsod Ng Maynila, Philippines.
Research Article
World Journal of Advanced Research and Reviews, 2024, 24(03), 2177-2186
Publication history:
Received on 11 November 2024; revised on 18 December 2024; accepted on 20 December 2024
Abstract:
Named Entity Recognition (NER) is a crucial natural language processing task that extracts and classifies named entities from unstructured text into predefined categories. While existing NER methods have shown success in general domains, they often face significant challenges when applied to specialized contexts like Filipino cultural and historical texts. These challenges stem from the unique linguistic features, and diverse naming conventions. This research introduces an enhanced rule-based NER approach that specifically addresses these challenges. At its core, the system utilizes curated Corpus of Historical Filipino and Philippine English (COHFIE), which serves as both training and evaluation data. This research presents an enhanced rule-based approach for NER using a Corpus of Historical Filipino and Philippine English (COHFIE) building on pattern-learning methods, incorporating character and token features, and by using positive and negative example sets. To enrich the classification process, we used the International Committee for Documentation – Conceptual Reference Model (CIDOC-CRM), a cultural heritage framework, to provide a more nuanced categorization of entities based on their historical and cultural significance. Tested across existing Filipino based models (calamanCy and RoBERTa), the enhanced model shows improvement on identifying entities related to Filipino culture (CUL) and history terms (PER, ORG, LOC).
Keywords:
Named Entity Recognition; Natural Language Processing; Filipino Corpus; CIDOC-CRM
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0