Measuring cross-language intelligibility between Romance languages with computational tools
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911430874234880 |
|---|---|
| author | Dinu, Liviu P Uban, Ana Sabina Iordache, Bogdan Dinu, Anca Georgescu, Simona |
| author_facet | Dinu, Liviu P Uban, Ana Sabina Iordache, Bogdan Dinu, Anca Georgescu, Simona |
| contents | We present an analysis of mutual intelligibility in related languages applied for languages in the Romance family. We introduce a novel computational metric for estimating intelligibility based on lexical similarity using surface and semantic similarity of related words, and use it to measure mutual intelligibility for the five main Romance languages (French, Italian, Portuguese, Spanish, and Romanian), and compare results using both the orthographic and phonetic forms of words as well as different parallel corpora and vectorial models of word meaning representation. The obtained intelligibility scores confirm intuitions related to intelligibility asymmetry across languages and significantly correlate with results of cloze tests in human experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07447 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Measuring cross-language intelligibility between Romance languages with computational tools Dinu, Liviu P Uban, Ana Sabina Iordache, Bogdan Dinu, Anca Georgescu, Simona Computation and Language We present an analysis of mutual intelligibility in related languages applied for languages in the Romance family. We introduce a novel computational metric for estimating intelligibility based on lexical similarity using surface and semantic similarity of related words, and use it to measure mutual intelligibility for the five main Romance languages (French, Italian, Portuguese, Spanish, and Romanian), and compare results using both the orthographic and phonetic forms of words as well as different parallel corpora and vectorial models of word meaning representation. The obtained intelligibility scores confirm intuitions related to intelligibility asymmetry across languages and significantly correlate with results of cloze tests in human experiments. |
| title | Measuring cross-language intelligibility between Romance languages with computational tools |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.07447 |