@inproceedings{basirat-etal-2026-computational,
title = "A Computational Approach to Language Contact {--} A Case Study of {P}ersian",
author = "Basirat, Ali and
Namazifard, Danial and
Hemmati, Navid Baradaran",
editor = "Merchant, Rayyan and
Megerdoomian, Karine",
booktitle = "The Proceedings of the First Workshop on {NLP} and {LLM}s for the {I}ranian Language Family",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.silkroadnlp-1.5/",
pages = "38--49",
ISBN = "979-8-89176-371-5",
abstract = "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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basirat-etal-2026-computational">
<titleInfo>
<title>A Computational Approach to Language Contact – A Case Study of Persian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Basirat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danial</namePart>
<namePart type="family">Namazifard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Navid</namePart>
<namePart type="given">Baradaran</namePart>
<namePart type="family">Hemmati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rayyan</namePart>
<namePart type="family">Merchant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karine</namePart>
<namePart type="family">Megerdoomian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-371-5</identifier>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">basirat-etal-2026-computational</identifier>
<location>
<url>https://aclanthology.org/2026.silkroadnlp-1.5/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>38</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Computational Approach to Language Contact – A Case Study of Persian
%A Basirat, Ali
%A Namazifard, Danial
%A Hemmati, Navid Baradaran
%Y Merchant, Rayyan
%Y Megerdoomian, Karine
%S The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-371-5
%F basirat-etal-2026-computational
%X 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.
%U https://aclanthology.org/2026.silkroadnlp-1.5/
%P 38-49
Markdown (Informal)
[A Computational Approach to Language Contact – A Case Study of Persian](https://aclanthology.org/2026.silkroadnlp-1.5/) (Basirat et al., SilkRoadNLP 2026)
ACL