# Modelling the Morphology of Verbal Paradigms: A Case Study in the Tokenization of Turkish and Hebrew

arXiv: https://arxiv.org/abs/2602.05648 · HTML: https://mlsanity.com/paper/2602.05648/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 60 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://mlsanity.com/paper/2103.06874/) (2021)
- [Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models](https://mlsanity.com/paper/2305.13707/) (2023)
- [When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models](https://mlsanity.com/paper/2010.12858/) (2020)
- [Syntactic Structure from Deep Learning](https://mlsanity.com/paper/2004.10827/) (2020)
- [MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2504.02768/) (2025)
- [Impact of Tokenization on Language Models: An Analysis for Turkish](https://mlsanity.com/paper/2204.08832/) (2022)
- [Synthetic Data Generation Using Large Language Models: Advances in Text and Code](https://mlsanity.com/paper/2503.14023/) (2025)
- [Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs](https://mlsanity.com/paper/1909.02597/) (2019)
- [Toward a Theory of Tokenization in LLMs](https://mlsanity.com/paper/2404.08335/) (2024)
- [How Much Does Tokenization Affect Neural Machine Translation?](https://mlsanity.com/paper/1812.08621/) (2018)
- [Verb Argument Structure Alternations in Word and Sentence Embeddings](https://mlsanity.com/paper/1811.10773/) (2018)
- [MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies](https://mlsanity.com/paper/2502.00894/) (2025)
- [Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English](https://mlsanity.com/paper/1707.09879/) (2017)
- [Bayes in the age of intelligent machines](https://mlsanity.com/paper/2311.10206/) (2023)
- [Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5](https://mlsanity.com/paper/2410.11627/) (2024)
- [How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure](https://mlsanity.com/paper/2311.04900/) (2023)
- [Blackbird language matrices (BLM), a new task for rule-like generalization in neural networks: Motivations and Formal Specifications](https://mlsanity.com/paper/2306.11444/) (2023)
- [Exploring syntactic information in sentence embeddings through multilingual subject-verb agreement](https://mlsanity.com/paper/2409.06567/) (2024)
- [Exploring Italian sentence embeddings properties through multi-tasking](https://mlsanity.com/paper/2409.06622/) (2024)
- [Explicit Morphological Knowledge Improves Pre-training of Language Models for Hebrew](https://mlsanity.com/paper/2311.00658/) (2023)
- [Blackbird's language matrices (BLMs): a new benchmark to investigate disentangled generalisation in neural networks](https://mlsanity.com/paper/2205.10866/) (2022)
- [Does Training on Synthetic Data Make Models Less Robust?](https://mlsanity.com/paper/2502.07164/) (2025)
- [Challenging the Abilities of Large Language Models in Italian: a Community Initiative](https://mlsanity.com/paper/2512.04759/) (2025)

## Built on by (most cited first, 2 of 2)

- [Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies](https://mlsanity.com/paper/2603.15295/) (2026)
- [Comparing Natural and Synthetic Structured Data: A Study of the Passive Verb Alternation in French and Italian](https://mlsanity.com/paper/2603.25227/) (2026)

## Abstract (arXiv)

We investigate how transformer models represent complex verb paradigms in Turkish and Modern Hebrew, concentrating on how tokenization strategies shape this ability. Using the Blackbird Language Matrices task on natural data, we show that for Turkish -- with its transparent morphological markers -- both monolingual and multilingual models succeed, either when tokenization is atomic or when it breaks words into small subword units. For Hebrew, instead, monolingual and multilingual models diverge. A multilingual model using character-level tokenization fails to capture the language non-concatenative morphology, but a monolingual model with morpheme-aware segmentation performs well. Performance improves on more synthetic datasets, in all models.