# HelaBERT: Enhancing Sinhala Language Understanding with Dual Pooling Classification Head

arXiv: https://arxiv.org/abs/2608.22922 · HTML: https://mlsanity.com/paper/2608.22922/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [CamemBERT: a Tasty French Language Model](https://mlsanity.com/paper/1911.03894/) (2019)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages](https://mlsanity.com/paper/2309.09400/) (2023)
- [PhoBERT: Pre-trained language models for Vietnamese](https://mlsanity.com/paper/2003.00744/) (2020)
- [RobBERT: a Dutch RoBERTa-based Language Model](https://mlsanity.com/paper/2001.06286/) (2020)
- [Survey on Publicly Available Sinhala Natural Language Processing Tools and Research](https://mlsanity.com/paper/1906.02358/) (2019)
- [BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification](https://mlsanity.com/paper/2208.07864/) (2022)
- [SinLlama -- A Large Language Model for Sinhala](https://mlsanity.com/paper/2508.09115/) (2025)
- [Sentiment Analysis for Sinhala Language using Deep Learning Techniques](https://mlsanity.com/paper/2011.07280/) (2020)
- [Exploiting Parallel Corpora to Improve Multilingual Embedding based Document and Sentence Alignment](https://mlsanity.com/paper/2106.06766/) (2021)

## Abstract (arXiv)

We present HelaBERT, a family of two BERT-based masked language models pre-trained from scratch on approximately 1 billion tokens of Sinhala text sourced from MADLAD-400, CulturaX, and a custom corpus comprising news articles, Sinhala Wikipedia, and web crawl data. HelaBERT-Small (~23.3M parameters, 6 layers) and HelaBERT-Large (~110M parameters, 12 layers) both use a SentencePiece Unigram tokenizer (vocabulary size 32,000) tailored to Sinhala's agglutinative morphology and complex script. We evaluate both models on four downstream Sinhala text classification tasks: news category classification, news source classification, sentiment analysis, and writing style classification, using 5 independent seed runs with stratified 80/20 train/test splits. We additionally propose a dual pooling classification head and evaluate it systematically across all four tasks, finding consistent improvements on sentiment analysis and a moderate gain on news category classification for HelaBERT-Small, while the standard [CLS]-linear head remains competitive on news source classification, a headline-level task with short average input length. We release both models to support further research in Sinhala NLP.