CebuaNER: A New Baseline Cebuano Named Entity Recognition Model

TL;DR

This paper introduces CebuaNER, a baseline Cebuano NER model trained on a large annotated news corpus, achieving over 70% in key metrics and showing promise for crosslingual applications.

Contribution

It presents the first large-scale annotated Cebuano news corpus and a baseline NER model, advancing NLP resources for underrepresented Southeast Asian languages.

Findings

Achieved over 70% precision, recall, and F1 scores across entity tags.

Collected and annotated over 4,000 Cebuano news articles.

Demonstrated potential for crosslingual NER with Tagalog.

Abstract

Despite being one of the most linguistically diverse groups of countries, computational linguistics and language processing research in Southeast Asia has struggled to match the level of countries from the Global North. Thus, initiatives such as open-sourcing corpora and the development of baseline models for basic language processing tasks are important stepping stones to encourage the growth of research efforts in the field. To answer this call, we introduce CebuaNER, a new baseline model for named entity recognition (NER) in the Cebuano language. Cebuano is the second most-used native language in the Philippines, with over 20 million speakers. To build the model, we collected and annotated over 4,000 news articles, the largest of any work in the language, retrieved from online local Cebuano platforms to train algorithms such as Conditional Random Field and Bidirectional LSTM. Our findings show promising results as a new baseline model, achieving over 70% performance on precision, recall, and F1 across all entity tags, as well as potential efficacy in a crosslingual setup with Tagalog.