Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.20592 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912855034429440 |
|---|---|
| author | Basirat, Ali Namazifard, Danial Hemmati, Navid Baradaran |
| author_facet | Basirat, Ali Namazifard, Danial Hemmati, Navid Baradaran |
| contents | We investigate structural traces of language contact in the intermediate representations of a monolingual language model. Focusing on Persian (Farsi) as a historically contact-rich language, we probe the representations of a Persian-trained model when exposed to languages with varying degrees and types of contact with Persian. Our methodology quantifies the amount of linguistic information encoded in intermediate representations and assesses how this information is distributed across model components for different morphosyntactic features. The results show that universal syntactic information is largely insensitive to historical contact, whereas morphological features such as Case and Gender are strongly shaped by language-specific structure, suggesting that contact effects in monolingual language models are selective and structurally constrained. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20592 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Computational Approach to Language Contact -- A Case Study of Persian Basirat, Ali Namazifard, Danial Hemmati, Navid Baradaran Computation and Language We investigate structural traces of language contact in the intermediate representations of a monolingual language model. Focusing on Persian (Farsi) as a historically contact-rich language, we probe the representations of a Persian-trained model when exposed to languages with varying degrees and types of contact with Persian. Our methodology quantifies the amount of linguistic information encoded in intermediate representations and assesses how this information is distributed across model components for different morphosyntactic features. The results show that universal syntactic information is largely insensitive to historical contact, whereas morphological features such as Case and Gender are strongly shaped by language-specific structure, suggesting that contact effects in monolingual language models are selective and structurally constrained. |
| title | A Computational Approach to Language Contact -- A Case Study of Persian |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.20592 |