# Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment

arXiv: https://arxiv.org/abs/2508.08424 · HTML: https://mlsanity.com/paper/2508.08424/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 67 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling](https://mlsanity.com/paper/1312.3005/) (2013)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [MuRIL: Multilingual Representations for Indian Languages](https://mlsanity.com/paper/2103.10730/) (2021)
- [MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages](https://mlsanity.com/paper/2204.08582/) (2022)
- [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021)
- [Large Language Models Meet NLP: A Survey](https://mlsanity.com/paper/2405.12819/) (2024)
- [Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages](https://mlsanity.com/paper/2212.05409/) (2022)
- [Why do language models perform worse for morphologically complex languages?](https://mlsanity.com/paper/2411.14198/) (2024)
- [Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance](https://mlsanity.com/paper/2403.06265/) (2024)
- [Tokenization and the Noiseless Channel](https://mlsanity.com/paper/2306.16842/) (2023)
- [Are All Languages Equally Hard to Language-Model?](https://mlsanity.com/paper/1806.03743/) (2018)
- [AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages](https://mlsanity.com/paper/2005.00085/) (2020)
- [IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages](https://mlsanity.com/paper/2203.05437/) (2022)
- [Comparing Biases and the Impact of Multilingual Training across Multiple Languages](https://mlsanity.com/paper/2305.11242/) (2023)
- [Greed is All You Need: An Evaluation of Tokenizer Inference Methods](https://mlsanity.com/paper/2403.01289/) (2024)
- [BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training](https://mlsanity.com/paper/2409.04599/) (2024)
- [Analyzing Cognitive Plausibility of Subword Tokenization](https://mlsanity.com/paper/2310.13348/) (2023)
- [IndicXNLI: Evaluating Multilingual Inference for Indian Languages](https://mlsanity.com/paper/2204.08776/) (2022)
- [MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies](https://mlsanity.com/paper/2502.00894/) (2025)
- [Evaluating Morphological Alignment of Tokenizers in 70 Languages](https://mlsanity.com/paper/2507.06378/) (2025)
- [Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models](https://mlsanity.com/paper/2205.06130/) (2022)

## Built on by (most cited first, 9 of 9)

- [MinGram: A Minimalist Unigram Tokenizer with High Compression and Competitive Morphological Alignment](https://mlsanity.com/paper/2606.27019/) (2026)
- [Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation](https://mlsanity.com/paper/2608.25089/) (2026)
- [Contextual morphologically-guided tokenization for Latin encoder models](https://mlsanity.com/paper/2511.09709/) (2025)
- [Tokenization and Morphological Fidelity in Uralic NLP: A Cross-Lingual Evaluation](https://mlsanity.com/paper/2602.04241/) (2026)
- [LangMAP: A Language-Adaptive Approach to Tokenization](https://mlsanity.com/paper/2606.23566/) (2026)
- [What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?](https://mlsanity.com/paper/2608.17325/) (2026)
- [MoirfEolas and Cr'iochScore: Developing Resources for and the Evaluation of Tokenization Alignment with Irish Morphology](https://mlsanity.com/paper/2609.05022/) (2026)
- [The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models](https://mlsanity.com/paper/2609.17553/) (2026)
- [Preserving Morphemes: Morphology-Guided Pre-Tokenization for Nepali](https://mlsanity.com/paper/2609.33395/) (2026)

## Abstract (arXiv)

The relationship between tokenizer algorithm (e.g., Byte-Pair Encoding (BPE), Unigram), morphological alignment, tokenization quality (e.g., compression efficiency), and downstream performance remains largely unclear, particularly for languages with complex morphology. In this paper, we conduct a comprehensive evaluation of tokenizers using small-sized BERT models -- from pre-training through fine-tuning -- for Telugu (agglutinative), along with preliminary evaluation in Hindi (primarily fusional with some agglutination) and English (fusional). To evaluate morphological alignment of tokenizers in Telugu, we create a dataset containing gold morpheme segmentations of 600 derivational and 7000 inflectional word forms. Our experiments reveal two key findings for Telugu. First, the choice of tokenizer algorithm is the most significant factor influencing performance, with Unigram-based tokenizers consistently outperforming BPE across most settings. Second, while better morphological alignment shows a moderate, positive correlation with performance on text classification and structure prediction tasks, its impact is secondary to the tokenizer algorithm. Notably, hybrid approaches that use morphological information for pre-segmentation significantly boost the performance of BPE, though not Unigram. Our results further showcase the need for comprehensive intrinsic evaluation metrics for tokenizers that could explain downstream performance trends consistently.