---
title: "Why do language models perform worse for morphologically"
description: "For the first cause, they introduce MorphScore, a metric of how well token boundaries match… 113 references, cited by 52 papers here."
authors: ["Catherine Arnett", "Benjamin Bergen"]
year: 2025
venue: "Proceedings of the 31st International Conference on Computational Linguistics"
source: "https://aclanthology.org/2025.coling-main.441/"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/arnett-2025-why-do-language-models-perform/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/arnett-2025-why-do-language-models-perform/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/2/) / Why do language models perform worse for morphologically complex languages?

# Why do language models perform worse for morphologically complex languages?

**Authors:** [Catherine Arnett](https://md.research.elamur.ai/free/en/authors/catherine-arnett/) and [Benjamin Bergen](https://md.research.elamur.ai/free/en/authors/benjamin-bergen/) · **Year:** 2025 · **Venue:** [Proceedings of the 31st International Conference on Computational Linguistics](https://md.research.elamur.ai/free/en/venues/coling/) ([COLING 2025](https://md.research.elamur.ai/free/en/venues/coling/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.coling-main.441/) · [PDF](https://aclanthology.org/2025.coling-main.441.pdf) · [OpenAlex](https://openalex.org/W4404652853)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [52](https://md.research.elamur.ai/free/en/papers/arnett-2025-why-do-language-models-perform/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Language models tend to perform better on fusional languages such as English than on agglutinative ones such as Turkish. Earlier work blamed morphological complexity. Arnett and Bergen first confirm this gap and extend earlier analyses to larger transformer models, both monolingual and multilingual. They then test three possible causes. The first is tokenizers that ignore morpheme boundaries. The second is generally weaker tokenization, measured by compression and Rényi entropy. The third is unequal training data. For the first cause, they introduce MorphScore, a metric of how well token boundaries match morpheme boundaries, with evaluation data for 22 languages built from Universal Dependencies and UniMorph. Morphological alignment does not explain the gap, and tokenization quality accounts for only a small part of it. The gap mostly vanishes when monolingual models are trained on datasets equalized by "byte premium", which adjusts for how many bytes each language and script needs to encode comparable content. The authors conclude that morphological type does not make a language inherently harder to model. Correctly measured data quantity matters most, which is a practical lesson for low-resource and multilingual training.

## Key points
- The study replicates the agglutinative–fusional performance gap reported by Cotterell et al. (2018) and Gerz et al. (2018a), whose earlier sample covered 50 languages.
- MorphScore is presented as the first multilingual evaluation of tokenizer morphological alignment. It covers 22 languages and is released at github.com/catherinearnett/morphscore, with all code and data also on OSF.
- No evidence links morphological alignment to the gap. Rényi entropy shows a small effect, while compression is examined as the other quality measure.
- Training on byte-premium-scaled data removes most of the gap. In the Goldfish models, the byte-premium difference between morphological types is only marginally significant.
- Limitations include few languages with typology annotations and uneven UD/UniMorph data across languages. Only a single morpheme boundary, inflectional or derivational, is scored per word.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of California San Diego](https://md.research.elamur.ai/free/en/universities/university-of-california-san-diego/) — University, San Diego, United States · 73 works · 51,948 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 828 works · [🧩 Morphology](https://md.research.elamur.ai/free/en/topics/morphology/) · 405 works

## Cite

Cite as: Catherine Arnett and Benjamin Bergen. 2025. Why do language models perform worse for morphologically complex languages?. Proceedings of the 31st International Conference on Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{arnett2025why,
  title = {{Why do language models perform worse for morphologically complex languages?}},
  author = {Catherine Arnett and Benjamin Bergen},
  booktitle = {Proceedings of the 31st International Conference on Computational Linguistics},
  year = {2025},
  url = {https://aclanthology.org/2025.coling-main.441/}
}
```

- [← previous AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails](https://md.research.elamur.ai/free/en/papers/ghosh-2025-aegis2-0-diverse-ai-safety/)
- [next → Evaluating the Capabilities of Large Language Models for Multi-label Emotion Understanding](https://md.research.elamur.ai/free/en/papers/belay-2025-evaluating-capabilities-large-language-models/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/2/)

## References

113 references, 30 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ayimunishagu Abulimiti and Tanja Schultz. 2020. Building language models for morphological rich low-resource languages using data from related donor languages: the case of Uyghur. In Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collab… [find](https://scholar.google.com/scholar?q=Ayimunishagu+Abulimiti+and+Tanja+Schultz%2E+2020%2E+Building+language+models+for+morphological+rich+low%2Dresource+languages+using+data+from+related+donor+languages%3A+the+case+of+Uyghur%2E+In+Proceedings+of+th)
2. Farrell Ackerman and Robert Malouf. 2013. Morphological organization: The low conditional entropy conjecture. Language, 89(3):429–464. [find](https://scholar.google.com/scholar?q=Farrell+Ackerman+and+Robert+Malouf%2E+2013%2E+Morphological+organization%3A+The+low+conditional+entropy+conjecture%2E+Language%2C+89%283%29%3A429%E2%80%93464%2E)
3. David Adelani, Hannah Liu, Xiaoyu Shen, Nikita Vassilyev, Jesujoba Alabi, Yanke Mao, Haonan Gao, and En-Shiun Lee. 2024. [SIB-200: A simple, inclusive, and big evaluation dataset for topic classification in 200+ languages and dialects](https://md.research.elamur.ai/free/en/papers/adelani-2023-sib-200-simple-inclusive-big/). In Proceedings of the 18th Conference of the European Chapter of…
4. Aranes, Glyd Jun and Zeman, Dan . 2021. Ud cebuano-gja. Accessed: 2024-09-04. [find](https://scholar.google.com/scholar?q=Aranes%2C+Glyd+Jun+and+Zeman%2C+Dan+%2E+2021%2E+Ud+cebuano%2Dgja%2E+Accessed%3A+2024%2D09%2D04%2E)
5. Maria Jesus Aranzabe, Aitziber Atutxa, Kepa Bengoetxea, Koldo Gojenola, and Larraitz Uria. 2015. Automatic conversion of the basque dependency treebank to universal dependencies. In Proceedings of the fourteenth international workshop on treebanks an linguistic theories (TLT14), pages 233–241. [find](https://scholar.google.com/scholar?q=Maria+Jesus+Aranzabe%2C+Aitziber+Atutxa%2C+Kepa+Bengoetxea%2C+Koldo+Gojenola%2C+and+Larraitz+Uria%2E+2015%2E+Automatic+conversion+of+the+basque+dependency+treebank+to+universal+dependencies%2E+In+Proceedings+of+the)
6. Catherine Arnett, Tyler A. Chang, and Benjamin Bergen. 2024a. A bit of a problem: Measurement disparities in dataset sizes across languages. In Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024, pages 1–9, Torino, Italia. ELRA and ICC… [find](https://scholar.google.com/scholar?q=Catherine+Arnett%2C+Tyler+A%2E+Chang%2C+and+Benjamin+Bergen%2E+2024a%2E+A+bit+of+a+problem%3A+Measurement+disparities+in+dataset+sizes+across+languages%2E+In+Proceedings+of+the+3rd+Annual+Meeting+of+the+Special+Int)
7. Catherine Arnett, Pamela D Rivière, Tyler Chang, and Sean Trott. 2024b. Different tokenization schemes lead to comparable performance in Spanish number agreement. In Proceedings of the 21st SIGMOR-PHON workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 32–38, Mexico C… [find](https://scholar.google.com/scholar?q=Catherine+Arnett%2C+Pamela+D+Rivie%CC%80re%2C+Tyler+Chang%2C+and+Sean+Trott%2E+2024b%2E+Different+tokenization+schemes+lead+to+comparable+performance+in+Spanish+number+agreement%2E+In+Proceedings+of+the+21st+SIGMOR%2DPH)
8. Mohammad Atari, Mona J Xue, Peter S Park, Damián We would like to thank the UC San Diego Social Blasi, and Joseph Henrich. 2023. Which humans? Sciences Computing Facility Team for the use of the Social Sciences Research and Development En- Mark Baker. 1996. The polysynthesis parameter. Oxford Studi… [find](https://scholar.google.com/scholar?q=Mohammad+Atari%2C+Mona+J+Xue%2C+Peter+S+Park%2C+Damia%CC%81n+We+would+like+to+thank+the+UC+San+Diego+Social+Blasi%2C+and+Joseph+Henrich%2E+2023%2E+Which+humans%3F+Sciences+Computing+Facility+Team+for+the+use+of+the+Soci)
9. Douglas M Bates. 2010. lme4: Mixed-effects modeling with R. [find](https://scholar.google.com/scholar?q=Douglas+M+Bates%2E+2010%2E+lme4%3A+Mixed%2Deffects+modeling+with+R%2E)
10. Thomas Bauwens and Pieter Delobelle. 2024. BPE-knockout: Pruning pre-existing BPE tokenisers with backwards-compatible morphological semi-supervision. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Vo… [find](https://scholar.google.com/scholar?q=Thomas+Bauwens+and+Pieter+Delobelle%2E+2024%2E+BPE%2Dknockout%3A+Pruning+pre%2Dexisting+BPE+tokenisers+with+backwards%2Dcompatible+morphological+semi%2Dsupervision%2E+In+Proceedings+of+the+2024+Conference+of+the+Nort)
11. Jatayu Baxi and Brijesh Bhatt. 2021. Morpheme boundary detection & grammatical feature prediction for Gujarati : Dataset & model. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 369–377, National Institute of Technology Silchar, Silchar, India. NLP As… [find](https://scholar.google.com/scholar?q=Jatayu+Baxi+and+Brijesh+Bhatt%2E+2021%2E+Morpheme+boundary+detection+%26+grammatical+feature+prediction+for+Gujarati+%3A+Dataset+%26+model%2E+In+Proceedings+of+the+18th+International+Conference+on+Natural+Languag)
12. Emily M Bender. 2011. On achieving and evaluating language-independence in NLP. Linguistic Issues in Language Technology, 6. [find](https://scholar.google.com/scholar?q=Emily+M+Bender%2E+2011%2E+On+achieving+and+evaluating+language%2Dindependence+in+NLP%2E+Linguistic+Issues+in+Language+Technology%2C+6%2E)
13. Thomas Berg, Peter Zörnig, and Charlotte Lehr. 2022. The effects of type and token frequency on word length: a cross-linguistic study. Glottotheory, 13(2):173–209. [find](https://scholar.google.com/scholar?q=Thomas+Berg%2C+Peter+Zo%CC%88rnig%2C+and+Charlotte+Lehr%2E+2022%2E+The+effects+of+type+and+token+frequency+on+word+length%3A+a+cross%2Dlinguistic+study%2E+Glottotheory%2C+13%282%29%3A173%E2%80%93209%2E)
14. Riyaz Ahmad Bhat, Rajesh Bhatt, Annahita Farudi, Prescott Klassen, Bhuvana Narasimhan, Martha Palmer, Owen Rambow, Dipti Misra Sharma, Ashwini Vaidya, Sri Ramagurumurthy Vishnu, et al. 2017. The hindi/urdu treebank project. In Handbook of Linguistic Annotation. Springer Press. [find](https://scholar.google.com/scholar?q=Riyaz+Ahmad+Bhat%2C+Rajesh+Bhatt%2C+Annahita+Farudi%2C+Prescott+Klassen%2C+Bhuvana+Narasimhan%2C+Martha+Palmer%2C+Owen+Rambow%2C+Dipti+Misra+Sharma%2C+Ashwini+Vaidya%2C+Sri+Ramagurumurthy+Vishnu%2C+et+al%2E+2017%2E+The+hindi)
15. Damian Blasi, Antonios Anastasopoulos, and Graham Neubig. 2022. [Systematic inequalities in language technology performance across the world’s languages](https://md.research.elamur.ai/free/en/papers/blasi-2022-systematic-inequalities-language-technology-performance/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5486–5505, Dublin, Irelan…
16. Kaj Bostrom and Greg Durrett. 2020. [Byte pair encoding is suboptimal for language model pretraining](https://md.research.elamur.ai/free/en/papers/bostrom-2020-byte-pair-encoding-is-suboptimal/). In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4617–4624, Online. Association for Computational Linguistics.
17. Georgie Botev, Arya D. McCarthy, Winston Wu, and David Yarowsky. 2022. Deciphering and characterizing out-of-vocabulary words for morphologically rich languages. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5309–5326, Gyeongju, Republic of Korea. Internatio… [find](https://scholar.google.com/scholar?q=Georgie+Botev%2C+Arya+D%2E+McCarthy%2C+Winston+Wu%2C+and+David+Yarowsky%2E+2022%2E+Deciphering+and+characterizing+out%2Dof%2Dvocabulary+words+for+morphologically+rich+languages%2E+In+Proceedings+of+the+29th+Internation)
18. Dunstan Patrick Brown. 2010. Morphological typology. In Handbook of Linguistic Typology, pages 487–503. Oxford University Press. [find](https://scholar.google.com/scholar?q=Dunstan+Patrick+Brown%2E+2010%2E+Morphological+typology%2E+In+Handbook+of+Linguistic+Typology%2C+pages+487%E2%80%93503%2E+Oxford+University+Press%2E)
19. Tyler A Chang, Catherine Arnett, Zhuowen Tu, and Benjamin K Bergen. 2023. [When Is Multilinguality a Curse?](https://md.research.elamur.ai/free/en/papers/chang-2024-when-is-multilinguality-curse-language/) Language Modeling for 250 High-and Low-Resource Languages. arXiv preprint arXiv:2311.09205.
20. Tyler A Chang, Catherine Arnett, Zhuowen Tu, and Benjamin K Bergen. 2024. Goldfish: Monolingual Language Models for 350 Languages. arXiv preprint arXiv:2408.10441. [find](https://scholar.google.com/scholar?q=Tyler+A+Chang%2C+Catherine+Arnett%2C+Zhuowen+Tu%2C+and+Benjamin+K+Bergen%2E+2024%2E+Goldfish%3A+Monolingual+Language+Models+for+350+Languages%2E+arXiv+preprint+arXiv%3A2408%2E10441%2E)
21. Pavel Chizhov, Catherine Arnett, Elizaveta Korotkova, and Ivan P. Yamshchikov. 2024. BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training. Preprint, arXiv:arXiv:2409.04599. Preprint. [find](https://scholar.google.com/scholar?q=Pavel+Chizhov%2C+Catherine+Arnett%2C+Elizaveta+Korotkova%2C+and+Ivan+P%2E+Yamshchikov%2E+2024%2E+BPE+Gets+Picky%3A+Efficient+Vocabulary+Refinement+During+Tokenizer+Training%2E+Preprint%2C+arXiv%3AarXiv%3A2409%2E04599%2E+Prepri)
22. Sanghyun Choo and Wonjoon Kim. 2023. A study on the evaluation of tokenizer performance in natural language processing. Applied Artificial Intelligence, 37(1):2175112. [find](https://scholar.google.com/scholar?q=Sanghyun+Choo+and+Wonjoon+Kim%2E+2023%2E+A+study+on+the+evaluation+of+tokenizer+performance+in+natural+language+processing%2E+Applied+Artificial+Intelligence%2C+37%281%29%3A2175112%2E)
23. Monojit Choudhury. 2023. Generative AI has a language problem. Nature Human Behaviour, 7(11):1802–1803. [find](https://scholar.google.com/scholar?q=Monojit+Choudhury%2E+2023%2E+Generative+AI+has+a+language+problem%2E+Nature+Human+Behaviour%2C+7%2811%29%3A1802%E2%80%931803%2E)
24. Jayeol Chun, Na-Rae Han, Jena D. Hwang, and Jinho D. Choi. 2018. Building Universal Dependency treebanks in Korean. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Jayeol+Chun%2C+Na%2DRae+Han%2C+Jena+D%2E+Hwang%2C+and+Jinho+D%2E+Choi%2E+2018%2E+Building+Universal+Dependency+treebanks+in+Korean%2E+In+Proceedings+of+the+Eleventh+International+Conference+on+Language+Resources+and+Ev)
25. Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel Bowman, Holger Schwenk, and Veselin Stoyanov. 2018. XNLI: Evaluating cross-lingual sentence representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2475–2485, Brussels, Bel… [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Ruty+Rinott%2C+Guillaume+Lample%2C+Adina+Williams%2C+Samuel+Bowman%2C+Holger+Schwenk%2C+and+Veselin+Stoyanov%2E+2018%2E+XNLI%3A+Evaluating+cross%2Dlingual+sentence+representations%2E+In+Proceedings+of+the)
26. Ryan Cotterell, Sabrina J. Mielke, Jason Eisner, and Brian Roark. 2018. [Are all languages equally hard to language-model?](https://md.research.elamur.ai/free/en/papers/cotterell-2018-are-all-languages-equally-hard/) In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages…
27. Gautier Dagan, Gabriel Synnaeve, and Baptiste Roziere. 2024. [Getting the most out of your tokenizer for pre-training and domain adaptation](https://md.research.elamur.ai/free/en/papers/dagan-2024-getting-most-out-tokenizer-pre/). In Forty-first International Conference on Machine Learning.
28. Gregoire Deletang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li Kevin Wenliang, Matthew Aitchison, Laurent Orseau, Marcus Hutter, and Joel Veness. 2024. [Language modeling is compression](https://md.research.elamur.ai/free/en/papers/deletang-2023-language-modeling-compression/). In The Twelfth International Conference on Learning R…
29. Kaja Dobrovoljc, Tomaž Erjavec, and Simon Krek. 2017. The Universal Dependencies treebank for Slovenian. In Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing, pages 33– 38, Valencia, Spain. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Kaja+Dobrovoljc%2C+Tomaz%CC%8C+Erjavec%2C+and+Simon+Krek%2E+2017%2E+The+Universal+Dependencies+treebank+for+Slovenian%2E+In+Proceedings+of+the+6th+Workshop+on+Balto%2DSlavic+Natural+Language+Processing%2C+pages+33%E2%80%93+38%2C+)
30. Ximena Gutierrez-Vasques, Christian Bentz, and Tanja Samardžić. 2023. [Languages through the looking glass of BPE compression](https://md.research.elamur.ai/free/en/papers/vasques-2023-languages-through-looking-glass-bpe/). Computational Linguistics, 49(4):943–1001.
31. Kaja Dobrovoljc and Nikola Ljubešić. 2022. Extending the SSJ Universal Dependencies treebank for Slovenian: Was it worth it? In Proceedings of the 16th Linguistic Annotation Workshop (LAW-XVI) within LREC2022, pages 15–22, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Kaja+Dobrovoljc+and+Nikola+Ljubes%CC%8Cic%CC%81%2E+2022%2E+Extending+the+SSJ+Universal+Dependencies+treebank+for+Slovenian%3A+Was+it+worth+it%3F+In+Proceedings+of+the+16th+Linguistic+Annotation+Workshop+%28LAW%2DXVI%29+withi)
32. Dilek Z Hakkani-Tür, Kemal Oflazer, and Gökhan Tür. 2002. Statistical morphological disambiguation for agglutinative languages. Computers and the Humanities, 36:381–410. [find](https://scholar.google.com/scholar?q=Dilek+Z+Hakkani%2DTu%CC%88r%2C+Kemal+Oflazer%2C+and+Go%CC%88khan+Tu%CC%88r%2E+2002%2E+Statistical+morphological+disambiguation+for+agglutinative+languages%2E+Computers+and+the+Humanities%2C+36%3A381%E2%80%93410%2E)
33. Wolfgang U Dressler. 2010. A typological approach to first language acquisition. Language acquisition across linguistic and cognitive systems, 52:109–124. [find](https://scholar.google.com/scholar?q=Wolfgang+U+Dressler%2E+2010%2E+A+typological+approach+to+first+language+acquisition%2E+Language+acquisition+across+linguistic+and+cognitive+systems%2C+52%3A109%E2%80%93124%2E)
34. Matthew S. Dryer and Martin Haspelmath. 2013. WALS Online (v2020.3). [find](https://scholar.google.com/scholar?q=Matthew+S%2E+Dryer+and+Martin+Haspelmath%2E+2013%2E+WALS+Online+%28v2020%2E3%29%2E)
35. Gertraud Fenk-Oczlon and August Fenk. 1999. Cognition, quantitative linguistics, and systemic typology. Linguistic Typology, 3:151–177. [find](https://scholar.google.com/scholar?q=Gertraud+Fenk%2DOczlon+and+August+Fenk%2E+1999%2E+Cognition%2C+quantitative+linguistics%2C+and+systemic+typology%2E+Linguistic+Typology%2C+3%3A151%E2%80%93177%2E)
36. Matthias Gallé. 2019. Investigating the effectiveness of BPE: The power of shorter sequences. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1375–1381, Hong Kon… [find](https://scholar.google.com/scholar?q=Matthias+Galle%CC%81%2E+2019%2E+Investigating+the+effectiveness+of+BPE%3A+The+power+of+shorter+sequences%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Language+Processing+and+the+9th+Int)
37. Daniela Gerz, Ivan Vulić, Edoardo Ponti, Jason Naradowsky, Roi Reichart, and Anna Korhonen. 2018a. [Language modeling for morphologically rich languages: Character-aware modeling for word-level prediction](https://md.research.elamur.ai/free/en/papers/gerz-2018-language-modeling-morphologically-rich-languages/). Transactions of the Association for Computational Linguistics, 6:451–465.
38. Daniela Gerz, Ivan Vulić, Edoardo Maria Ponti, Roi Reichart, and Anna Korhonen. 2018b. [On the relation between linguistic typology and (limitations of) multilingual language modeling](https://md.research.elamur.ai/free/en/papers/gerz-2018-relation-between-linguistic-typology-limitations/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 316–327, Brussels,…
39. Omer Goldman, Avi Caciularu, Matan Eyal, Kris Cao, Idan Szpektor, and Reut Tsarfaty. 2024. Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance. arXiv preprint arXiv:2403.06265. [find](https://scholar.google.com/scholar?q=Omer+Goldman%2C+Avi+Caciularu%2C+Matan+Eyal%2C+Kris+Cao%2C+Idan+Szpektor%2C+and+Reut+Tsarfaty%2E+2024%2E+Unpacking+Tokenization%3A+Evaluating+Text+Compression+and+its+Correlation+with+Model+Performance%2E+arXiv+preprin)
40. Eylon Gueta, Omer Goldman, and Reut Tsarfaty. 2023. [Explicit Morphological Knowledge Improves Pre-training of Language Models for Hebrew](https://md.research.elamur.ai/free/en/papers/gueta-2023-explicit-morphological-knowledge-improves-pre/). arXiv e-prints, pages arXiv–2311.
41. Mandy Guo, Zihang Dai, Denny Vrandečić, and Rami Al-Rfou. 2020. Wiki-40B: Multilingual language model dataset. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2440–2452, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Mandy+Guo%2C+Zihang+Dai%2C+Denny+Vrandec%CC%8Cic%CC%81%2C+and+Rami+Al%2DRfou%2E+2020%2E+Wiki%2D40B%3A+Multilingual+language+model+dataset%2E+In+Proceedings+of+the+Twelfth+Language+Resources+and+Evaluation+Conference%2C+pages+2440%E2%80%93)
42. Martin Haspelmath. 2009. An empirical test of the Agglutination Hypothesis. Universals of language today, pages 13–29. [find](https://scholar.google.com/scholar?q=Martin+Haspelmath%2E+2009%2E+An+empirical+test+of+the+Agglutination+Hypothesis%2E+Universals+of+language+today%2C+pages+13%E2%80%9329%2E)
43. Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, Tom Hennigan, Eric Noland, Katie Millican, George van den Driessche, Bogdan Damoc, Aurelia Guy, Simon Osindero, Karen Simonyan, E… — [Training Compute-Optimal Large Language Models](https://md.research.elamur.ai/free/en/papers/hoffmann-2022-training-compute-optimal-large-language/)
44. Valentin Hofmann, Janet Pierrehumbert, and Hinrich Schütze. 2021. [Superbizarre is not superb: Derivational morphology improves BERT’s interpretation of complex words](https://md.research.elamur.ai/free/en/papers/hofmann-2021-superbizarre-derivational/). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conferen…
45. Valentin Hofmann, Hinrich Schuetze, and Janet Pierrehumbert. 2022. An embarrassingly simple method to mitigate undesirable properties of pretrained language model tokenizers. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 38… [find](https://scholar.google.com/scholar?q=Valentin+Hofmann%2C+Hinrich+Schuetze%2C+and+Janet+Pierrehumbert%2E+2022%2E+An+embarrassingly+simple+method+to+mitigate+undesirable+properties+of+pretrained+language+model+tokenizers%2E+In+Proceedings+of+the+60t)
46. Haris Jabbar. 2023. MorphPiece: Moving away from Statistical Language Representation. arXiv preprint arXiv:2307.07262. — [arXiv:2307.07262](https://arxiv.org/abs/2307.07262) [find](https://scholar.google.com/scholar?q=Haris+Jabbar%2E+2023%2E+MorphPiece%3A+Moving+away+from+Statistical+Language+Representation%2E+arXiv+preprint+arXiv%3A2307%2E07262%2E+%E2%80%94+%5BarXiv%3A2307%2E07262%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2307%2E07262%29)
47. Pratik Joshi, Sebastin Santy, Amar Budhiraja, Kalika Bali, and Monojit Choudhury. 2020. [The state and fate of linguistic diversity and inclusion in the NLP world](https://md.research.elamur.ai/free/en/papers/joshi-2020-state-fate-linguistic-diversity-inclusion/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6282–6293, Online. Association for Comp…
48. Julie Kallini, Isabel Papadimitriou, Richard Futrell, Kyle Mahowald, and Christopher Potts. 2024. [Mission: Impossible language models](https://md.research.elamur.ai/free/en/papers/kallini-2024-mission-impossible-language-models/). arXiv preprint arXiv:2401.06416.
49. Yiğit Bekir Kaya and A Cüneyd Tantuğ. 2024. Effect of tokenization granularity for Turkish large language models. Intelligent Systems with Applications, 21:200335. [find](https://scholar.google.com/scholar?q=Yig%CC%86it+Bekir+Kaya+and+A+Cu%CC%88neyd+Tantug%CC%86%2E+2024%2E+Effect+of+tokenization+granularity+for+Turkish+large+language+models%2E+Intelligent+Systems+with+Applications%2C+21%3A200335%2E)
50. Simran Khanuja, Sebastian Ruder, and Partha Talukdar. 2023. Evaluating the diversity, equity, and inclusion of NLP technology: A case study for Indian languages. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1763–1777, Dubrovnik, Croatia. Association for Computationa… [find](https://scholar.google.com/scholar?q=Simran+Khanuja%2C+Sebastian+Ruder%2C+and+Partha+Talukdar%2E+2023%2E+Evaluating+the+diversity%2C+equity%2C+and+inclusion+of+NLP+technology%3A+A+case+study+for+Indian+languages%2E+In+Findings+of+the+Association+for+Com)
51. Christo Kirov, Ryan Cotterell, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sabrina J. Mielke, Arya McCarthy, Sandra Kübler, David Yarowsky, Jason Eisner, and Mans Hulden. 2018. [UniMorph 2.0: Universal Morphology](https://md.research.elamur.ai/free/en/papers/kirov-2018-unimorph-2-0-universal-morphology/). In Proceedings of the Eleventh Internati…
52. Stav Klein and Reut Tsarfaty. 2020. Getting the \#\#life out of living: How adequate are word-pieces for modelling complex morphology? In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 204–209, Online. Association for Computational… [find](https://scholar.google.com/scholar?q=Stav+Klein+and+Reut+Tsarfaty%2E+2020%2E+Getting+the+%5C%23%5C%23life+out+of+living%3A+How+adequate+are+word%2Dpieces+for+modelling+complex+morphology%3F+In+Proceedings+of+the+17th+SIGMORPHON+Workshop+on+Computational+R)
53. Taku Kudo and John Richardson. 2018. [SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing](https://md.research.elamur.ai/free/en/papers/kudo-2018-sentencepiece-simple-language-independent-subword/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 66–71, Brussels, Belgium. Associ…
54. Septina Dian Larasati, Vladislav Kuboň, and Daniel Zeman. 2011. Indonesian morphology tool (morphind): Towards an indonesian corpus. In Systems and Frameworks for Computational Morphology: Second International Workshop, SFCM 2011, Zurich, Switzerland, August 26, 2011. Proceedings 2, pages 119–129.… [find](https://scholar.google.com/scholar?q=Septina+Dian+Larasati%2C+Vladislav+Kubon%CC%8C%2C+and+Daniel+Zeman%2E+2011%2E+Indonesian+morphology+tool+%28morphind%29%3A+Towards+an+indonesian+corpus%2E+In+Systems+and+Frameworks+for+Computational+Morphology%3A+Second+Int)
55. Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, et al. 2023. Bloom: A 176b-parameter open-access multilingual language model. [find](https://scholar.google.com/scholar?q=Teven+Le+Scao%2C+Angela+Fan%2C+Christopher+Akiki%2C+Ellie+Pavlick%2C+Suzana+Ilic%CC%81%2C+Daniel+Hesslow%2C+Roman+Castagne%CC%81%2C+Alexandra+Sasha+Luccioni%2C+Franc%CC%A7ois+Yvon%2C+Matthias+Galle%CC%81%2C+et+al%2E+2023%2E+Bloom%3A+A+176b%2Dparame)
56. Jungseob Lee, Hyeonseok Moon, Seungjun Lee, Chanjun Park, Sugyeong Eo, Hyunwoong Ko, Jaehyung Seo, Seungyoon Lee, and Heuiseok Lim. 2024. Length-aware byte pair encoding for mitigating over-segmentation in Korean machine translation. In Findings of the Association for Computational Linguistics ACL 2… [find](https://scholar.google.com/scholar?q=Jungseob+Lee%2C+Hyeonseok+Moon%2C+Seungjun+Lee%2C+Chanjun+Park%2C+Sugyeong+Eo%2C+Hyunwoong+Ko%2C+Jaehyung+Seo%2C+Seungyoon+Lee%2C+and+Heuiseok+Lim%2E+2024%2E+Length%2Daware+byte+pair+encoding+for+mitigating+over%2Dsegmentati)
57. Davis Liang, Hila Gonen, Yuning Mao, Rui Hou, Naman Goyal, Marjan Ghazvininejad, Luke Zettlemoyer, and Madian Khabsa. 2023. [XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models](https://md.research.elamur.ai/free/en/papers/liang-2023-xlm-v-overcoming-vocabulary-bottleneck/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, p…
58. Jindřich Libovickỳ and Jindřich Helcl. 2024. Lexically grounded subword segmentation. arXiv preprint arXiv:2406.13560. [find](https://scholar.google.com/scholar?q=Jindr%CC%8Cich+Libovicky%CC%80+and+Jindr%CC%8Cich+Helcl%2E+2024%2E+Lexically+grounded+subword+segmentation%2E+arXiv+preprint+arXiv%3A2406%2E13560%2E)
59. Peiqin Lin, Shaoxiong Ji, Jörg Tiedemann, André FT Martins, and Hinrich Schütze. 2024. [MaLA-500: Massive Language Adaptation of Large Language Models](https://md.research.elamur.ai/free/en/papers/lin-2024-mala-500-massive-language-adaptation/). arXiv preprint arXiv:2401.13303.
60. Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O’Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyano… — [Few-shot Learning with Multilingual Language Models](https://md.research.elamur.ai/free/en/papers/lin-2021-few-shot-learning-multilingual-language/)
61. Irina Lobzhanidze. 2022. Finite-State Computational Morphology. Springer. [find](https://scholar.google.com/scholar?q=Irina+Lobzhanidze%2E+2022%2E+Finite%2DState+Computational+Morphology%2E+Springer%2E)
62. Teresa Lynn and Jennifer Foster. 2016. Universal Dependencies for Irish. In Proceedings of the Second Celtic Language Technology Workshop, Paris, France. [find](https://scholar.google.com/scholar?q=Teresa+Lynn+and+Jennifer+Foster%2E+2016%2E+Universal+Dependencies+for+Irish%2E+In+Proceedings+of+the+Second+Celtic+Language+Technology+Workshop%2C+Paris%2C+France%2E)
63. Dominik Macháček, Jonáš Vidra, and Ondřej Bojar. 2018. Morphological and language-agnostic word segmentation for NMT. In International Conference on Text, Speech, and Dialogue, pages 277–284. Springer. [find](https://scholar.google.com/scholar?q=Dominik+Macha%CC%81c%CC%8Cek%2C+Jona%CC%81s%CC%8C+Vidra%2C+and+Ondr%CC%8Cej+Bojar%2E+2018%2E+Morphological+and+language%2Dagnostic+word+segmentation+for+NMT%2E+In+International+Conference+on+Text%2C+Speech%2C+and+Dialogue%2C+pages+277%E2%80%93284%2E+Spr)
64. Kosuke Matsuzaki, Masaya Taniguchi, Kentaro Inui, and Keisuke Sakaguchi. 2024. J-UniMorph: Japanese morphological annotation through the universal feature schema. In Proceedings of the 21st SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 7–19, Mexico City… [find](https://scholar.google.com/scholar?q=Kosuke+Matsuzaki%2C+Masaya+Taniguchi%2C+Kentaro+Inui%2C+and+Keisuke+Sakaguchi%2E+2024%2E+J%2DUniMorph%3A+Japanese+morphological+annotation+through+the+universal+feature+schema%2E+In+Proceedings+of+the+21st+SIGMORPHON)
65. Benjamin Minixhofer, Jonas Pfeiffer, and Ivan Vulić. 2023. CompoundPiece: Evaluating and improving decompounding performance of language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 343–359, Singapore. Association for Computational Linguis… [find](https://scholar.google.com/scholar?q=Benjamin+Minixhofer%2C+Jonas+Pfeiffer%2C+and+Ivan+Vulic%CC%81%2E+2023%2E+CompoundPiece%3A+Evaluating+and+improving+decompounding+performance+of+language+models%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Met)
66. Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng Xin Yong, Hailey Schoelkopf, Xiangru Tang, Dragomir Radev, Alham Fikri Aji, Khalid Almubarak, Samuel Albanie, Zaid Alyafeai, Albert Webson, Edward Raff, and Colin Raffel.… — [Crosslingual Generalization through Multitask Finetuning](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-crosslingual-generalization-through-multitask-finetuning/)
67. NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia-Gonzalez, Prangthip Hansanti, John H… [find](https://scholar.google.com/scholar?q=NLLB+Team%2C+Marta+R%2E+Costa%2Djussa%CC%80%2C+James+Cross%2C+Onur+C%CC%A7elebi%2C+Maha+Elbayad%2C+Kenneth+Heafield%2C+Kevin+Heffernan%2C+Elahe+Kalbassi%2C+Janice+Lam%2C+Daniel+Licht%2C+Jean+Maillard%2C+Anna+Sun%2C+Skyler+Wang%2C+Guillaume+)
68. Antoine Nzeyimana and Andre Niyongabo Rubungo. 2022. KinyaBERT: a morphology-aware Kinyarwanda language model. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5347–5363, Dublin, Ireland. Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Antoine+Nzeyimana+and+Andre+Niyongabo+Rubungo%2E+2022%2E+KinyaBERT%3A+a+morphology%2Daware+Kinyarwanda+language+model%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computational+Linguistic)
69. Martha Palmer, Rajesh Bhatt, Bhuvana Narasimhan, Owen Rambow, Dipti Misra Sharma, and Fei Xia. 2009. Hindi syntax: Annotating dependency, lexical predicate-argument structure, and phrase structure. In The 7th International Conference on Natural Language Processing, pages 14–17. [find](https://scholar.google.com/scholar?q=Martha+Palmer%2C+Rajesh+Bhatt%2C+Bhuvana+Narasimhan%2C+Owen+Rambow%2C+Dipti+Misra+Sharma%2C+and+Fei+Xia%2E+2009%2E+Hindi+syntax%3A+Annotating+dependency%2C+lexical+predicate%2Dargument+structure%2C+and+phrase+structure%2E+In)
70. Hyunji Hayley Park, Katherine J Zhang, Coleman Haley, Kenneth Steimel, Han Liu, and Lane Schwartz. 2021. [Morphology matters: A multilingual language modeling analysis](https://md.research.elamur.ai/free/en/papers/park-2021-morphology-matters-multilingual-language-modeling/). Transactions of the Association for Computational Linguistics, 9:261–276.
71. Aleksandar Petrov, Emanuele La Malfa, Philip Torr, and Adel Bibi. 2023. [Language model tokenizers introduce unfairness between languages](https://md.research.elamur.ai/free/en/papers/petrov-2023-language-model-tokenizers-introduce-unfairness/). In Advances in Neural Information Processing Systems, volume 36, pages 36963–36990. Curran Associates, Inc.
72. Tiago Pimentel, Maria Ryskina, Sabrina J. Mielke, Shijie Wu, Eleanor Chodroff, Brian Leonard, Garrett Nicolai, Yustinus Ghanggo Ate, Salam Khalifa, Nizar Habash, Charbel El-Khaissi, Omer Goldman, Michael Gasser, William Lane, Matt Coler, Arturo Oncevay, Jaime Rafael Montoya Samame, Gema Celeste Silv… [find](https://scholar.google.com/scholar?q=Tiago+Pimentel%2C+Maria+Ryskina%2C+Sabrina+J%2E+Mielke%2C+Shijie+Wu%2C+Eleanor+Chodroff%2C+Brian+Leonard%2C+Garrett+Nicolai%2C+Yustinus+Ghanggo+Ate%2C+Salam+Khalifa%2C+Nizar+Habash%2C+Charbel+El%2DKhaissi%2C+Omer+Goldman%2C+Mich)
73. SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages. In Proceedings of the 18th SIGMOR-PHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 229–259, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=SIGMORPHON+2021+Shared+Task+on+Morphological+Reinflection%3A+Generalization+Across+Languages%2E+In+Proceedings+of+the+18th+SIGMOR%2DPHON+Workshop+on+Computational+Research+in+Phonetics%2C+Phonology%2C+and+Morph)
74. Mārcis Pinnis, Rihards Krišlauks, Daiga Deksne, and Toms Miks. 2017. Neural machine translation for morphologically rich languages with improved subword units and synthetic data. In Text, Speech, and Dialogue: 20th International Conference, TSD 2017, Prague, Czech Republic, August 27-31, 2017, Pro… [find](https://scholar.google.com/scholar?q=Ma%CC%84rcis+Pinnis%2C+Rihards+Kris%CC%8Clauks%2C+Daiga+Deksne%2C+and+Toms+Miks%2E+2017%2E+Neural+machine+translation+for+morphologically+rich+languages+with+improved+subword+units+and+synthetic+data%2E+In+Text%2C+Speech%2C+an)
75. Frans Plank. 1991. Of abundance and scantiness in inflection: A typological prelude. Paradigms: the economy of inflection, pages 1–39. [find](https://scholar.google.com/scholar?q=Frans+Plank%2E+1991%2E+Of+abundance+and+scantiness+in+inflection%3A+A+typological+prelude%2E+Paradigms%3A+the+economy+of+inflection%2C+pages+1%E2%80%9339%2E)
76. Frans Plank. 1999. Split morphology: How agglutination and flexion mix. Linguistic Typology, 3:279– 340. [find](https://scholar.google.com/scholar?q=Frans+Plank%2E+1999%2E+Split+morphology%3A+How+agglutination+and+flexion+mix%2E+Linguistic+Typology%2C+3%3A279%E2%80%93+340%2E)
77. Edoardo Maria Ponti, Goran Glavaš, Olga Majewska, Qianchu Liu, Ivan Vulić, and Anna Korhonen. 2020. [XCOPA: A multilingual dataset for causal commonsense reasoning](https://md.research.elamur.ai/free/en/papers/ponti-2020-xcopa-multilingual-dataset-causal-commonsense/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2362–2376, Online. Associatio…
78. Prokopis Prokopidis and Haris Papageorgiou. 2014. Experiments for dependency parsing of Greek. In Proceedings of the First Joint Workshop on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical Languages, pages 90–96, Dublin, Ireland. Dublin City University. [find](https://scholar.google.com/scholar?q=Prokopis+Prokopidis+and+Haris+Papageorgiou%2E+2014%2E+Experiments+for+dependency+parsing+of+Greek%2E+In+Proceedings+of+the+First+Joint+Workshop+on+Statistical+Parsing+of+Morphologically+Rich+Languages+and+S)
79. Loganathan Ramasamy and Zdeněk Žabokrtský. 2012. Prague dependency style treebank for Tamil. In Proceedings of Eighth International Conference on Language Resources and Evaluation (LREC 2012), pages 1888–1894, İstanbul, Turkey. [find](https://scholar.google.com/scholar?q=Loganathan+Ramasamy+and+Zdene%CC%8Ck+Z%CC%8Cabokrtsky%CC%81%2E+2012%2E+Prague+dependency+style+treebank+for+Tamil%2E+In+Proceedings+of+Eighth+International+Conference+on+Language+Resources+and+Evaluation+%28LREC+2012%29%2C+page)
80. Krithika Ramesh, Sunayana Sitaram, and Monojit Choudhury. 2023. Fairness in language models beyond English: Gaps and challenges. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2106–2119, Dubrovnik, Croatia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Krithika+Ramesh%2C+Sunayana+Sitaram%2C+and+Monojit+Choudhury%2E+2023%2E+Fairness+in+language+models+beyond+English%3A+Gaps+and+challenges%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EACL+2023)
81. Surangika Ranathunga and Nisansa de Silva. 2022. Some languages are more equal than others: Probing deeper into the linguistic disparity in the NLP world. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Join… [find](https://scholar.google.com/scholar?q=Surangika+Ranathunga+and+Nisansa+de+Silva%2E+2022%2E+Some+languages+are+more+equal+than+others%3A+Probing+deeper+into+the+linguistic+disparity+in+the+NLP+world%2E+In+Proceedings+of+the+2nd+Conference+of+the+A)
82. Mohammad Sadegh Rasooli, Manouchehr Kouhestani, and Amirsaeid Moloodi. 2013. Development of a Persian syntactic dependency treebank. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 306– 314, Atla… [find](https://scholar.google.com/scholar?q=Mohammad+Sadegh+Rasooli%2C+Manouchehr+Kouhestani%2C+and+Amirsaeid+Moloodi%2E+2013%2E+Development+of+a+Persian+syntactic+dependency+treebank%2E+In+Proceedings+of+the+2013+Conference+of+the+North+American+Chapter)
83. Eirı́kur Rögnvaldsson, Anton Karl Ingason, Einar Freyr SigurDsson, and Joel Wallenberg. 2012. [The Icelandic parsed historical corpus (IcePaHC)](https://md.research.elamur.ai/free/en/papers/rognvaldsson-2012-icelandic-parsed-historical-corpus-icepahc/). In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 1977–1984, Istanbul, Turkey. European Language…
84. Xinying Song, Alex Salcianu, Yang Song, Dave Dopson, and Denny Zhou. 2021. Fast WordPiece Tokenization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2089–2103, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Xinying+Song%2C+Alex+Salcianu%2C+Yang+Song%2C+Dave+Dopson%2C+and+Denny+Zhou%2E+2021%2E+Fast+WordPiece+Tokenization%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages)
85. Phillip Rust, Jonas Pfeiffer, Ivan Vulić, Sebastian Ruder, and Iryna Gurevych. 2021. [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://md.research.elamur.ai/free/en/papers/rust-2021-how-good-is-your-tokenizer/). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Join…
86. Martin A. Stoffel, Shinichi Nakagawa, and Holger Schielzeth. 2024. partr2: Partitioning r2 in glmms. Https://CRAN.R-project.org/package=partR2. [find](https://scholar.google.com/scholar?q=Martin+A%2E+Stoffel%2C+Shinichi+Nakagawa%2C+and+Holger+Schielzeth%2E+2024%2E+partr2%3A+Partitioning+r2+in+glmms%2E+Https%3A%2F%2FCRAN%2ER%2Dproject%2Eorg%2Fpackage%3DpartR2%2E)
87. Jonne Saleva and Constantine Lignos. 2021. The effectiveness of morphology-aware segmentation in low-resource neural machine translation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 164–174, Online.… [find](https://scholar.google.com/scholar?q=Jonne+Saleva+and+Constantine+Lignos%2E+2021%2E+The+effectiveness+of+morphology%2Daware+segmentation+in+low%2Dresource+neural+machine+translation%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Chapter+)
88. Dominiek Sandra. 1994. The morphology of the mental lexicon: Internal word structure viewed from a psycholinguistic perspective. Language and cognitive processes, 9(3):227–269. [find](https://scholar.google.com/scholar?q=Dominiek+Sandra%2E+1994%2E+The+morphology+of+the+mental+lexicon%3A+Internal+word+structure+viewed+from+a+psycholinguistic+perspective%2E+Language+and+cognitive+processes%2C+9%283%29%3A227%E2%80%93269%2E)
89. Craig W Schmidt, Varshini Reddy, Haoran Zhang, Alec Alameddine, Omri Uzan, Yuval Pinter, and Chris Tanner. 2024. [Tokenization is more than compression](https://md.research.elamur.ai/free/en/papers/schmidt-2024-tokenization-is-more-than-compression/). arXiv preprint arXiv:2402.18376.
90. Samson Tan, Shafiq Joty, Lav Varshney, and Min-Yen Kan. 2020. Mind your inflections! Improving NLP for non-standard Englishes with Base-Inflection Encoding. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5647–5663, Online. Association for Com… [find](https://scholar.google.com/scholar?q=Samson+Tan%2C+Shafiq+Joty%2C+Lav+Varshney%2C+and+Min%2DYen+Kan%2E+2020%2E+Mind+your+inflections%21+Improving+NLP+for+non%2Dstandard+Englishes+with+Base%2DInflection+Encoding%2E+In+Proceedings+of+the+2020+Conference+on+Em)
91. Mariona Taulé, M. Antònia Martı́, and Marta Recasens. 2008. AnCora: Multilevel annotated corpora for Catalan and Spanish. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Mariona+Taule%CC%81%2C+M%2E+Anto%CC%80nia+Mart%C4%B1%CC%81%2C+and+Marta+Recasens%2E+2008%2E+AnCora%3A+Multilevel+annotated+corpora+for+Catalan+and+Spanish%2E+In+Proceedings+of+the+Sixth+International+Conference+on+Language+Resources+a)
92. Ahmed Tawfik, Mahitab Emam, Khaled Essam, Robert Nabil, and Hany Hassan. 2019. [Morphology-aware word-segmentation in dialectal Arabic adaptation of neural machine translation](https://md.research.elamur.ai/free/en/papers/tawfik-2019-morphology-aware-word-segmentation-dialectal/). In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 11–17, Florence, Italy. Association for Comp…
93. Hyopil Shin and Hyunjo You. 2009. Hybrid n-gram probability estimation in morphologically rich languages. In Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation, pages 511–520. Waseda University. [find](https://scholar.google.com/scholar?q=Hyopil+Shin+and+Hyunjo+You%2E+2009%2E+Hybrid+n%2Dgram+probability+estimation+in+morphologically+rich+languages%2E+In+Proceedings+of+the+23rd+Pacific+Asia+Conference+on+Language%2C+Information+and+Computation%2C+p)
94. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288.
95. Kiril Simov, Petya Osenova, Alexander Simov, and Milen Kouylekov. 2005. Design and implementation of the bulgarian hpsg-based treebank. Journal of Research on Language and Computation. Special Issue, pages 495–522. [find](https://scholar.google.com/scholar?q=Kiril+Simov%2C+Petya+Osenova%2C+Alexander+Simov%2C+and+Milen+Kouylekov%2E+2005%2E+Design+and+implementation+of+the+bulgarian+hpsg%2Dbased+treebank%2E+Journal+of+Research+on+Language+and+Computation%2E+Special+Issue%2C+)
96. Omri Uzan, Craig W Schmidt, Chris Tanner, and Yuval Pinter. 2024. Greed is All You Need: An Evaluation of Tokenizer Inference Methods. arXiv preprint arXiv:2403.01289. [find](https://scholar.google.com/scholar?q=Omri+Uzan%2C+Craig+W+Schmidt%2C+Chris+Tanner%2C+and+Yuval+Pinter%2E+2024%2E+Greed+is+All+You+Need%3A+An+Evaluation+of+Tokenizer+Inference+Methods%2E+arXiv+preprint+arXiv%3A2403%2E01289%2E)
97. Dan I Slobin. 1973. Cognitive prerequisites for the development of grammar. In Studies of child language development, pages 175–208. Holt, Rinehart, & Winston. [find](https://scholar.google.com/scholar?q=Dan+I+Slobin%2E+1973%2E+Cognitive+prerequisites+for+the+development+of+grammar%2E+In+Studies+of+child+language+development%2C+pages+175%E2%80%93208%2E+Holt%2C+Rinehart%2C+%26+Winston%2E)
98. Veronika Vincze, Dóra Szauter, Attila Almási, György Móra, Zoltán Alexin, and János Csirik. 2010. Hungarian dependency treebank. In Proceedings of the Seventh Conference on International Language Resources and Evaluation, Valletta, Malta. [find](https://scholar.google.com/scholar?q=Veronika+Vincze%2C+Do%CC%81ra+Szauter%2C+Attila+Alma%CC%81si%2C+Gyo%CC%88rgy+Mo%CC%81ra%2C+Zolta%CC%81n+Alexin%2C+and+Ja%CC%81nos+Csirik%2E+2010%2E+Hungarian+dependency+treebank%2E+In+Proceedings+of+the+Seventh+Conference+on+International+Languag)
99. Dan I Slobin. 2001. Form-function relations: how do children find out what they are? Language acquisition and conceptual development, 3:406. [find](https://scholar.google.com/scholar?q=Dan+I+Slobin%2E+2001%2E+Form%2Dfunction+relations%3A+how+do+children+find+out+what+they+are%3F+Language+acquisition+and+conceptual+development%2C+3%3A406%2E)
100. Dan I Slobin. 2013. Crosslinguistic evidence for the language-making capacity. In The crosslinguistic study of language acquisition, pages 1157–1256. Psychology Press. [find](https://scholar.google.com/scholar?q=Dan+I+Slobin%2E+2013%2E+Crosslinguistic+evidence+for+the+language%2Dmaking+capacity%2E+In+The+crosslinguistic+study+of+language+acquisition%2C+pages+1157%E2%80%931256%2E+Psychology+Press%2E)
101. Anders Søgaard. 2022. [Should we ban English NLP for a year?](https://md.research.elamur.ai/free/en/papers/sogaard-2022-should-we-ban-english-nlp/) In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5254–5260, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
102. Ekaterina Vylomova, Jennifer White, Elizabeth Salesky, Sabrina J. Mielke, Shijie Wu, Edoardo Maria Ponti, Rowan Hall Maudslay, Ran Zmigrod, Josef Valvoda, Svetlana Toldova, Francis Tyers, Elena Klyachko, Ilya Yegorov, Natalia Krizhanovsky, Paula Czarnowska, Irene Nikkarinen, Andrew Krizhanovsky, Tia… [find](https://scholar.google.com/scholar?q=Ekaterina+Vylomova%2C+Jennifer+White%2C+Elizabeth+Salesky%2C+Sabrina+J%2E+Mielke%2C+Shijie+Wu%2C+Edoardo+Maria+Ponti%2C+Rowan+Hall+Maudslay%2C+Ran+Zmigrod%2C+Josef+Valvoda%2C+Svetlana+Toldova%2C+Francis+Tyers%2C+Elena+Klyach)
103. SIGMORPHON 2020 shared task 0: Typologically diverse morphological inflection. In Proceedings of the 17th SIGMORPHON • Hungarian: UD Hungarian-Szeged train split (Vincze et al., 2010) [find](https://scholar.google.com/scholar?q=SIGMORPHON+2020+shared+task+0%3A+Typologically+diverse+morphological+inflection%2E+In+Proceedings+of+the+17th+SIGMORPHON+%E2%80%A2+Hungarian%3A+UD+Hungarian%2DSzeged+train+split+%28Vincze+et+al%2E%2C+2010%29)
104. Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 1–39, Online. Association for Computational Linguistics. • Urdu: UD Urdu-UDTB train split (Palmer et al., 2009; Bhat et al., 2017) [find](https://scholar.google.com/scholar?q=Workshop+on+Computational+Research+in+Phonetics%2C+Phonology%2C+and+Morphology%2C+pages+1%E2%80%9339%2C+Online%2E+Association+for+Computational+Linguistics%2E+%E2%80%A2+Urdu%3A+UD+Urdu%2DUDTB+train+split+%28Palmer+et+al%2E%2C+2009%3B+Bhat+e)
105. Atsuki Yamaguchi, Aline Villavicencio, and Nikolaos Aletras. 2024. An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative LLM Inference. arXiv preprint arXiv:2402.10712. — [arXiv:2402.10712](https://arxiv.org/abs/2402.10712) [find](https://scholar.google.com/scholar?q=Atsuki+Yamaguchi%2C+Aline+Villavicencio%2C+and+Nikolaos+Aletras%2E+2024%2E+An+Empirical+Study+on+Cross%2Dlingual+Vocabulary+Adaptation+for+Efficient+Generative+LLM+Inference%2E+arXiv+preprint+arXiv%3A2402%2E10712%2E+%E2%80%94+)
106. Slovenian: UD Slovenian-SSJ train split (Dobrovoljc et al., 2017; Dobrovoljc and Ljubešić, 2022) [find](https://scholar.google.com/scholar?q=Slovenian%3A+UD+Slovenian%2DSSJ+train+split+%28Dobrovoljc+et+al%2E%2C+2017%3B+Dobrovoljc+and+Ljubes%CC%8Cic%CC%81%2C+2022%29)
107. Marat M. Yavrumyan and Anna S. Danielyan. 2020. Universal Dependencies and the Armenian Treebank. Herald of the Social Sciences, 2:231–244. [find](https://scholar.google.com/scholar?q=Marat+M%2E+Yavrumyan+and+Anna+S%2E+Danielyan%2E+2020%2E+Universal+Dependencies+and+the+Armenian+Treebank%2E+Herald+of+the+Social+Sciences%2C+2%3A231%E2%80%93244%2E)
108. Tamil: UD Tamil-TTB train split (Ramasamy and Žabokrtský, 2012) [find](https://scholar.google.com/scholar?q=Tamil%3A+UD+Tamil%2DTTB+train+split+%28Ramasamy+and+Z%CC%8Cabokrtsky%CC%81%2C+2012%29)
109. Amir Zeldes. 2017. The GUM corpus: Creating multilayer resources in the classroom. Language Resources and Evaluation, 51(3):581–612. [find](https://scholar.google.com/scholar?q=Amir+Zeldes%2E+2017%2E+The+GUM+corpus%3A+Creating+multilayer+resources+in+the+classroom%2E+Language+Resources+and+Evaluation%2C+51%283%29%3A581%E2%80%93612%2E)
110. Georgian: UD Georgian-GLC test split (Lobzhanidze, 2022) [find](https://scholar.google.com/scholar?q=Georgian%3A+UD+Georgian%2DGLC+test+split+%28Lobzhanidze%2C+2022%29)
111. Giulio Zhou. 2018. Morphological zero-shot neural machine translation. [find](https://scholar.google.com/scholar?q=Giulio+Zhou%2E+2018%2E+Morphological+zero%2Dshot+neural+machine+translation%2E)
112. Armenian: UD Armenian-BSUT train split (Yavrumyan and Danielyan, 2020) [find](https://scholar.google.com/scholar?q=Armenian%3A+UD+Armenian%2DBSUT+train+split+%28Yavrumyan+and+Danielyan%2C+2020%29)
113. Vilém Zouhar, Clara Meister, Juan Gastaldi, Li Du, Mrinmaya Sachan, and Ryan Cotterell. 2023. Tokenization and the noiseless channel. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5184–5207, Toronto, Canada. Association for… [find](https://scholar.google.com/scholar?q=Vile%CC%81m+Zouhar%2C+Clara+Meister%2C+Juan+Gastaldi%2C+Li+Du%2C+Mrinmaya+Sachan%2C+and+Ryan+Cotterell%2E+2023%2E+Tokenization+and+the+noiseless+channel%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+)

*Updated 30 October 2026*