---
title: "Cross-lingual Lexical Semantic Change in Romance — Uban 2026"
description: "The paper measures how far the meanings of etymologically related words have drifted apart in Romanian, Italian, Spanish, French and Portuguese, the five…"
authors: ["Ana Sabina Uban", "Liviu P Dinu", "Anca Daniela Dinu", "Simona Georgescu"]
year: 2026
venue: "The Proceedings for the 6th International Workshop on Computational Approaches to Language Change (LChange'26)"
source: "https://aclanthology.org/2026.lchange-1.4/"
doi: "10.18653/v1/2026.lchange-1.4"
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/uban-2026-cross-lingual-lexical-semantic-change/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/uban-2026-cross-lingual-lexical-semantic-change/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/5/) / Cross-lingual Lexical Semantic Change in Romance Languages

# Cross-lingual Lexical Semantic Change in Romance Languages

**Authors:** Ana Sabina Uban, [Liviu P Dinu](https://md.research.elamur.ai/free/en/authors/liviu-p-dinu/), Anca Daniela Dinu, Simona Georgescu · **Institutions:** [University of Bucharest](https://md.research.elamur.ai/free/en/universities/university-of-bucharest/) · **Year:** 2026 · **Venue:** The Proceedings for the 6th International Workshop on Computational Approaches to Language Change (LChange'26) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lchange-1.4/) · [PDF](https://aclanthology.org/2026.lchange-1.4.pdf) · [DOI 10.18653/v1/2026.lchange-1.4](https://doi.org/10.18653/v1/2026.lchange-1.4) · [OpenAlex](https://openalex.org/W7140081638)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
The paper measures how far the meanings of etymologically related words have drifted apart in Romanian, Italian, Spanish, French and Portuguese, the five principal members of the Romance family. Earlier computational work was mostly monolingual or limited to cognates. This study covers both inherited cognates and, apparently for the first time, borrowings between Romance languages. The word pairs come from RoBoCoP, a manually curated etymological database. Each word is represented with aligned static FastText vectors and with contextual vectors from a multilingual Sentence-BERT model, plus xlm-roberta-base in some runs. The contextual vectors are extracted from Wikipedia, Europarl and RomCro2.0. Divergence between paired words is scored with several distance methods, and the scores are then aggregated per language pair.

Static and contextual models largely agree on how language pairs rank. Spanish and Portuguese share the closest meanings. Romanian drifts furthest from its relatives, and Romanian–Portuguese is the most distant pair, which runs against Bartoli's lateral areas hypothesis. The released divergence lists give historical semantics a measurable, reusable resource.

## Key points
- **Data:** Cognates come from ProtoRom, the open subset of RoBoCoP, with 19,222 tuples. Borrowings total 46,490 pairs. All resulting divergence lists are published at nlp.unibuc.ro.
- **Distance methods:** Contextual embeddings are located in the corpora via Snowball stems. Distances are computed in three ways: mean-vector cosine, JSD over affinity-propagation clusters, and WiDiD cluster-centre distance.
- **Main choice of model:** Following earlier false-friend experiments, the authors focus mainly on Wikipedia-based models, both contextual with mean cosine distance and static with cosine distance.
- **Part of speech, cognates:** Verbs are the most stable (average distance 0.438), except in Romanian. Adverbs diverge most (0.523).
- **Part of speech, borrowings:** Adjectives are the most stable (0.449), mostly because borrowed adjectives tend to be relational. Overall, differences between parts of speech are small.

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

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

Topics: [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Lexical semantics & word embeddings](https://md.research.elamur.ai/free/en/topics/lexical-semantics/) · [Historical linguistics & language change](https://md.research.elamur.ai/free/en/topics/language-change/)

## Cite

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

```bibtex
@inproceedings{uban2026cross,
  title = {{Cross-lingual Lexical Semantic Change in Romance Languages}},
  author = {Uban, Ana Sabina and Dinu, Liviu P and Dinu, Anca Daniela and Georgescu, Simona},
  booktitle = {The Proceedings for the 6th International Workshop on Computational Approaches to Language Change (LChange'26)},
  year = {2026},
  doi = {10.18653/v1/2026.lchange-1.4},
  url = {https://doi.org/10.18653/v1/2026.lchange-1.4}
}
```

- [← previous Cross-Lingual and Cross-Cultural Transfer of Talk Move Classification to German Science Classrooms](https://md.research.elamur.ai/free/en/papers/wartena-2026-cross-lingual-cross-cultural-transfer/)
- [next → CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis](https://md.research.elamur.ai/free/en/papers/singh-2026-crossoracle-agentic-framework-real-time/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/5/)

## References

18 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Matteo G. Bartoli. 1925. Introduzione alla neolinguis-tica: Principi, scopi, metodi. Olschki, Firenze. [find](https://scholar.google.com/scholar?q=Matteo+G%2E+Bartoli%2E+1925%2E+Introduzione+alla+neolinguis%2Dtica%3A+Principi%2C+scopi%2C+metodi%2E+Olschki%2C+Firenze%2E)
2. Mihaela Bîrlădeanu, M. Iliescu, Liliana Macarie, Ioana Nichita, Mariana Ploae-Hănganu, Marius Sala, Maria Theban, and Ioana Vintilă-Rădulescu. 1988. Vocab-ularul reprezentativ al limbilor romanice. Editura Ştiinţifică şi Enciclopedică, Bucureşti. [find](https://scholar.google.com/scholar?q=Mihaela+B%C3%AErla%CC%86deanu%2C+M%2E+Iliescu%2C+Liliana+Macarie%2C+Ioana+Nichita%2C+Mariana+Ploae%2DHa%CC%86nganu%2C+Marius+Sala%2C+Maria+Theban%2C+and+Ioana+Vintila%CC%86%2DRa%CC%86dulescu%2E+1988%2E+Vocab%2Dularul+reprezentativ+al+limbilor+romanice)
3. Philipp Koehn. 2005. Europarl: A parallel corpus for statistical machine translation. In Proceedings of machine translation summit x: papers, pages 79–86. [find](https://scholar.google.com/scholar?q=Philipp+Koehn%2E+2005%2E+Europarl%3A+A+parallel+corpus+for+statistical+machine+translation%2E+In+Proceedings+of+machine+translation+summit+x%3A+papers%2C+pages+79%E2%80%9386%2E)
4. Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2016. Enriching Word Vectors with Subword Information. arXiv preprint arXiv:1607.04606. [find](https://scholar.google.com/scholar?q=Piotr+Bojanowski%2C+Edouard+Grave%2C+Armand+Joulin%2C+and+Tomas+Mikolov%2E+2016%2E+Enriching+Word+Vectors+with+Subword+Information%2E+arXiv+preprint+arXiv%3A1607%2E04606%2E)
5. Wilhelm Meyer-Lübke. 1911. Romanisches etymologisches wörterbuch, volume 3. C. Winter. [find](https://scholar.google.com/scholar?q=Wilhelm+Meyer%2DL%C3%BCbke%2E+1911%2E+Romanisches+etymologisches+w%C3%B6rterbuch%2C+volume+3%2E+C%2E+Winter%2E)
6. Bojana Mikelenić, Antoni Oliver, and Marko Tadić. 2024. Expansion of the romcro corpus with texts in catalan. In CLARIN Annual Conference Proceedings 2024, pages 135–139. Barcelona: CLARIN. [find](https://scholar.google.com/scholar?q=Bojana+Mikelenic%CC%81%2C+Antoni+Oliver%2C+and+Marko+Tadic%CC%81%2E+2024%2E+Expansion+of+the+romcro+corpus+with+texts+in+catalan%2E+In+CLARIN+Annual+Conference+Proceedings+2024%2C+pages+135%E2%80%93139%2E+Barcelona%3A+CLARIN%2E)
7. Jean-Paul Chauveau. 2016. Reconstruction comparative et histoire sémantique. In Éva Buchi and Wolfgang Schweickard, editors, Dictionnaire Étymologique Roman (DÉRom) 2. Pratique lexicographique et réflexions théoriques, pages 53–65. De Gruyter, Berlin/Boston. [find](https://scholar.google.com/scholar?q=Jean%2DPaul+Chauveau%2E+2016%2E+Reconstruction+comparative+et+histoire+s%C3%A9mantique%2E+In+%C3%89va+Buchi+and+Wolfgang+Schweickard%2C+editors%2C+Dictionnaire+%C3%89tymologique+Roman+%28D%C3%89Rom%29+2%2E+Pratique+lexicographique+et+r%C3%A9fl)
8. Syrielle Montariol and Alexandre Allauzen. 2021. Measure and evaluation of semantic divergence across two languages. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long P… [find](https://scholar.google.com/scholar?q=Syrielle+Montariol+and+Alexandre+Allauzen%2E+2021%2E+Measure+and+evaluation+of+semantic+divergence+across+two+languages%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Ling)
9. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Unsupervised cross-lingual representation learning at scale. CoRR, abs/1911.02116. [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Kartikay+Khandelwal%2C+Naman+Goyal%2C+Vishrav+Chaudhary%2C+Guillaume+Wenzek%2C+Francisco+Guzm%C3%A1n%2C+Edouard+Grave%2C+Myle+Ott%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+Unsupervised+cross%2Dlingu)
10. Francesco Periti, Alfio Ferrara, Stefano Montanelli, and Martin Ruskov. 2022. What is done is done: an incremental approach to semantic shift detection. In Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change, pages 33–43, Dublin, Ireland. Association for Computa… [find](https://scholar.google.com/scholar?q=Francesco+Periti%2C+Alfio+Ferrara%2C+Stefano+Montanelli%2C+and+Martin+Ruskov%2E+2022%2E+What+is+done+is+done%3A+an+incremental+approach+to+semantic+shift+detection%2E+In+Proceedings+of+the+3rd+Workshop+on+Computati)
11. Alexis Conneau, Guillaume Lample, Marc’Aurelio Ranzato, Ludovic Denoyer, and Hervé Jégou. 2017. Word translation without parallel data. arXiv preprint arXiv:1710.04087. [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Guillaume+Lample%2C+Marc%E2%80%99Aurelio+Ranzato%2C+Ludovic+Denoyer%2C+and+Herv%C3%A9+J%C3%A9gou%2E+2017%2E+Word+translation+without+parallel+data%2E+arXiv+preprint+arXiv%3A1710%2E04087%2E)
12. Liviu P Dinu, Ana Uban, Alina Cristea, Anca Dinu, Ioan-Bogdan Iordache, Simona Georgescu, and Laurentiu Zoicas. 2023. Robocop: A comprehensive romance borrowing cognate package and benchmark Francesco Periti and Nina Tahmasebi. 2024. A systematic comparison of contextualized word embeddings for lexi… [find](https://scholar.google.com/scholar?q=Liviu+P+Dinu%2C+Ana+Uban%2C+Alina+Cristea%2C+Anca+Dinu%2C+Ioan%2DBogdan+Iordache%2C+Simona+Georgescu%2C+and+Laurentiu+Zoicas%2E+2023%2E+Robocop%3A+A+comprehensive+romance+borrowing+cognate+package+and+benchmark+Francesco)
13. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Nils+Reimers+and+Iryna+Gurevych%2E+2019%2E+Sentence%2Dbert%3A+Sentence+embeddings+using+siamese+bert%2Dnetworks%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2E+Associ)
14. Sanda Reinheimer-Rîpeanu. 2001. Lingvistica romanică. Lexic – morfologie – fonetică. All, Bucarest. [find](https://scholar.google.com/scholar?q=Sanda+Reinheimer%2DR%C3%AEpeanu%2E+2001%2E+Lingvistica+romanica%CC%86%2E+Lexic+%E2%80%93+morfologie+%E2%80%93+fonetica%CC%86%2E+All%2C+Bucarest%2E)
15. Ana Sabina Uban, Alina Maria Ciobanu, and Liviu P Dinu. 2019. Studying Laws of Semantic Divergence across Languages using Cognate Sets. In Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change, pages 161–166. [find](https://scholar.google.com/scholar?q=Ana+Sabina+Uban%2C+Alina+Maria+Ciobanu%2C+and+Liviu+P+Dinu%2E+2019%2E+Studying+Laws+of+Semantic+Divergence+across+Languages+using+Cognate+Sets%2E+In+Proceedings+of+the+1st+International+Workshop+on+Computationa)
16. Ana Sabina Uban, Alina Maria Cristea, Anca Dinu, Liviu P. Dinu, Simona Georgescu, and Laurentiu Zoicas. 2021. Tracking semantic change in cognate sets for english and romance languages. In Proceedings of the 2nd International Workshop on Computational Approaches to Historical Language Change, pages… [find](https://scholar.google.com/scholar?q=Ana+Sabina+Uban%2C+Alina+Maria+Cristea%2C+Anca+Dinu%2C+Liviu+P%2E+Dinu%2C+Simona+Georgescu%2C+and+Laurentiu+Zoicas%2E+2021%2E+Tracking+semantic+change+in+cognate+sets+for+english+and+romance+languages%2E+In+Proceedings)
17. Ana Sabina Uban and Liviu P Dinu. 2020. Automatically Building a Multilingual Lexicon of False Friends With No Supervision. In Proceedings of LREC 2020, pages 3001–3007. [find](https://scholar.google.com/scholar?q=Ana+Sabina+Uban+and+Liviu+P+Dinu%2E+2020%2E+Automatically+Building+a+Multilingual+Lexicon+of+False+Friends+With+No+Supervision%2E+In+Proceedings+of+LREC+2020%2C+pages+3001%E2%80%933007%2E)
18. Ana Sabina Uban, Liviu P. Dinu, Bogdan Iordache, Simona Georgescu, and Claudia Vlad. 2025. Friend or foe? a computational investigation of semantic false friends across romance languages. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 15310–15324, On… [find](https://scholar.google.com/scholar?q=Ana+Sabina+Uban%2C+Liviu+P%2E+Dinu%2C+Bogdan+Iordache%2C+Simona+Georgescu%2C+and+Claudia+Vlad%2E+2025%2E+Friend+or+foe%3F+a+computational+investigation+of+semantic+false+friends+across+romance+languages%2E+In+Proceedin)