# textscCantoNLU: A benchmark for Cantonese natural language understanding

arXiv: https://arxiv.org/abs/2510.20670 · HTML: https://mlsanity.com/paper/2510.20670/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 64 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [CLUE: A Chinese Language Understanding Evaluation Benchmark](https://mlsanity.com/paper/2004.05986/) (2020)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects](https://mlsanity.com/paper/2309.07445/) (2023)
- [KLUE: Korean Language Understanding Evaluation](https://mlsanity.com/paper/2105.09680/) (2021)
- [IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding](https://mlsanity.com/paper/2009.05387/) (2020)
- [CLiMP: A Benchmark for Chinese Language Model Evaluation](https://mlsanity.com/paper/2101.11131/) (2021)
- [Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings](https://mlsanity.com/paper/2210.12623/) (2022)
- [URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base](https://mlsanity.com/paper/2409.18472/) (2024)
- [Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese](https://mlsanity.com/paper/2304.08823/) (2023)
- [HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs](https://mlsanity.com/paper/2503.12440/) (2025)
- [Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets](https://mlsanity.com/paper/2403.20056/) (2024)
- [Cross-lingual transfer of multilingual models on low resource African Languages](https://mlsanity.com/paper/2409.10965/) (2024)
- [Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarin](https://mlsanity.com/paper/1911.09271/) (2019)
- [Building UD Cairo for Old English in the Classroom](https://mlsanity.com/paper/2504.18718/) (2025)
- [SiniticMTError: A Machine Translation Dataset with Error Annotations for Sinitic Languages](https://mlsanity.com/paper/2509.20557/) (2025)

## Abstract (arXiv)

Cantonese, although spoken by millions, remains under-resourced due to policy and diglossia. To address this scarcity of evaluation frameworks for Cantonese, we introduce textscCantoNLU, a benchmark for Cantonese natural language understanding (NLU). This novel benchmark spans seven tasks covering syntax and semantics, including word sense disambiguation, linguistic acceptability judgment, language detection, natural language inference, sentiment analysis, part-of-speech tagging, and dependency parsing. In addition to the benchmark, we provide model baseline performance across a set of models: a Mandarin model without Cantonese training, two Cantonese-adapted models obtained by continual pre-training a Mandarin model on Cantonese text, and a monolingual Cantonese model trained from scratch. Results show that Cantonese-adapted models perform best overall, while monolingual models perform better on syntactic tasks. Mandarin models remain competitive in certain settings, indicating that direct transfer may be sufficient when Cantonese domain data is scarce. We release all datasets, code, and model weights to facilitate future research in Cantonese NLP.