# TabuLM: Morphology-Aware Tabular Pre-training for Low-Resource Languages

arXiv: https://arxiv.org/abs/2608.26923 · HTML: https://mlsanity.com/paper/2608.26923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 27 Aug 2026.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://mlsanity.com/paper/2103.06874/) (2021)
- [Rethinking Positional Encoding in Language Pre-training](https://mlsanity.com/paper/2006.15595/) (2020)
- [TABBIE: Pretrained Representations of Tabular Data](https://mlsanity.com/paper/2105.02584/) (2021)
- [KinyaBERT: a Morphology-aware Kinyarwanda Language Model](https://mlsanity.com/paper/2203.08459/) (2022)
- [Table Foundation Models: on knowledge pre-training for tabular learning](https://mlsanity.com/paper/2505.14415/) (2025)
- [TaTa: A Multilingual Table-to-Text Dataset for African Languages](https://mlsanity.com/paper/2211.00142/) (2022)
- [Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks](https://mlsanity.com/paper/2604.21696/) (2026)
- [M3TQA: Massively Multilingual Multitask Table Question Answering](https://mlsanity.com/paper/2508.16265/) (2025)
- [KinyaColBERT: A Lexically Grounded Retrieval Model for Low-Resource Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.03241/) (2025)

## Abstract (arXiv)

We present TabuLM, the first language model pre-trained on Kinyarwanda tabular data. Kinyarwanda is a morphologically rich Bantu language spoken by over 12 million people in Rwanda, yet lacks any dedicated tabular representation learning resource. TabuLM extends KinyaBERT-large, a two-tier morphological transformer, with additive row, column, and cell-type embeddings and a learned table-structure attention bias that sharpens same-row and same-column attention. Pre-training uses two new objectives: Masked Cell Recovery (MCR), which masks entire cells and forces reconstruction from row and column context, and Column Type Prediction (CTP), which predicts column semantic types from observed cell values. We pre-train on 172 Rwandan government tables (~35,000 cells) from NISR, RAB, REB, and MoH open-data portals, and introduce TabQA-kin, the first native Kinyarwanda table question-answering benchmark comprising 526 QA pairs across 31 tables and four question types. TabuLM achieves 62.0% exact match on TabQA-kin, outperforming KinyaBERT-large by 5.7 EM points and all multilingual baselines (mBERT 49.3%, XLM-R 50.0%) by 11.7-12.7 points. Analysis shows that structural table embeddings are most decisive for comparison and lookup questions, while morphological awareness provides complementary gains. Our code, data, and pre-trained checkpoint are publicly available.