@inproceedings{jafari-etal-2026-aparsin,
title = "{APARSIN}: A Multi-Variety Sentiment and Translation Benchmark for Iranic Languages",
author = "Jafari, Sadegh and
Azin, Tara and
Roodi, Farhad and
Tafti, Zahra Dehghani and
Ghadrdan, Mehrdad and
Esfahani, Elham Vatankhahan and
Naebzadeh, Aylin and
Shahhosseini, Mohammadhadi and
Khan, Ghafoor and
Forghani, Kazem and
Namazi, Danial and
Hashemi, Seyed Mohammad Hossein and
Farsi, Farhan and
Osoolian, Mohammad and
Mohammadi, Maede and
Zare, Mohammad Erfan and
Khan, Muhammad Hasnain and
Hussain, Muhammad and
Zaki, Nooreen and
Mohammadi, Joma and
Bali, Shayan and
Ranjbar, Mohammad Javad and
Lefever, Els and
Hoste, Veronique",
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-1.9/",
pages = "83--97",
ISBN = "979-8-89176-371-5",
abstract = "The Iranic language family includes many underrepresented languages and dialects that remain largely unexplored in modern NLP research. We introduce APARSIN, a multi-variety benchmark covering 14 Iranic languages, dialects, and accents, designed for sentiment analysis and machine translation. The dataset includes both high and low-resource varieties, several of which are endangered, capturing linguistic variation across them. We evaluate a set of instruction-tuned Large Language Models (LLMs) on these tasks and analyze their performance across the varieties. Our results highlight substantial performance gaps between standard Persian and other Iranic languages and dialects, demonstrating the need for more inclusive multilingual and dialectally diverse NLP benchmarks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jafari-etal-2026-aparsin">
<titleInfo>
<title>APARSIN: A Multi-Variety Sentiment and Translation Benchmark for Iranic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sadegh</namePart>
<namePart type="family">Jafari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tara</namePart>
<namePart type="family">Azin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farhad</namePart>
<namePart type="family">Roodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zahra</namePart>
<namePart type="given">Dehghani</namePart>
<namePart type="family">Tafti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehrdad</namePart>
<namePart type="family">Ghadrdan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elham</namePart>
<namePart type="given">Vatankhahan</namePart>
<namePart type="family">Esfahani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aylin</namePart>
<namePart type="family">Naebzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammadhadi</namePart>
<namePart type="family">Shahhosseini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ghafoor</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazem</namePart>
<namePart type="family">Forghani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danial</namePart>
<namePart type="family">Namazi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Mohammad</namePart>
<namePart type="given">Hossein</namePart>
<namePart type="family">Hashemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farhan</namePart>
<namePart type="family">Farsi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Osoolian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maede</namePart>
<namePart type="family">Mohammadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Erfan</namePart>
<namePart type="family">Zare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Hasnain</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Hussain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nooreen</namePart>
<namePart type="family">Zaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joma</namePart>
<namePart type="family">Mohammadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shayan</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Javad</namePart>
<namePart type="family">Ranjbar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</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>The Iranic language family includes many underrepresented languages and dialects that remain largely unexplored in modern NLP research. We introduce APARSIN, a multi-variety benchmark covering 14 Iranic languages, dialects, and accents, designed for sentiment analysis and machine translation. The dataset includes both high and low-resource varieties, several of which are endangered, capturing linguistic variation across them. We evaluate a set of instruction-tuned Large Language Models (LLMs) on these tasks and analyze their performance across the varieties. Our results highlight substantial performance gaps between standard Persian and other Iranic languages and dialects, demonstrating the need for more inclusive multilingual and dialectally diverse NLP benchmarks.</abstract>
<identifier type="citekey">jafari-etal-2026-aparsin</identifier>
<location>
<url>https://aclanthology.org/2026.silkroadnlp-1.9/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>83</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T APARSIN: A Multi-Variety Sentiment and Translation Benchmark for Iranic Languages
%A Jafari, Sadegh
%A Azin, Tara
%A Roodi, Farhad
%A Tafti, Zahra Dehghani
%A Ghadrdan, Mehrdad
%A Esfahani, Elham Vatankhahan
%A Naebzadeh, Aylin
%A Shahhosseini, Mohammadhadi
%A Khan, Ghafoor
%A Forghani, Kazem
%A Namazi, Danial
%A Hashemi, Seyed Mohammad Hossein
%A Farsi, Farhan
%A Osoolian, Mohammad
%A Mohammadi, Maede
%A Zare, Mohammad Erfan
%A Khan, Muhammad Hasnain
%A Hussain, Muhammad
%A Zaki, Nooreen
%A Mohammadi, Joma
%A Bali, Shayan
%A Ranjbar, Mohammad Javad
%A Lefever, Els
%A Hoste, Veronique
%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 jafari-etal-2026-aparsin
%X The Iranic language family includes many underrepresented languages and dialects that remain largely unexplored in modern NLP research. We introduce APARSIN, a multi-variety benchmark covering 14 Iranic languages, dialects, and accents, designed for sentiment analysis and machine translation. The dataset includes both high and low-resource varieties, several of which are endangered, capturing linguistic variation across them. We evaluate a set of instruction-tuned Large Language Models (LLMs) on these tasks and analyze their performance across the varieties. Our results highlight substantial performance gaps between standard Persian and other Iranic languages and dialects, demonstrating the need for more inclusive multilingual and dialectally diverse NLP benchmarks.
%U https://aclanthology.org/2026.silkroadnlp-1.9/
%P 83-97
Markdown (Informal)
[APARSIN: A Multi-Variety Sentiment and Translation Benchmark for Iranic Languages](https://aclanthology.org/2026.silkroadnlp-1.9/) (Jafari et al., SilkRoadNLP 2026)
ACL
- Sadegh Jafari, Tara Azin, Farhad Roodi, Zahra Dehghani Tafti, Mehrdad Ghadrdan, Elham Vatankhahan Esfahani, Aylin Naebzadeh, Mohammadhadi Shahhosseini, Ghafoor Khan, Kazem Forghani, Danial Namazi, Seyed Mohammad Hossein Hashemi, Farhan Farsi, Mohammad Osoolian, Maede Mohammadi, Mohammad Erfan Zare, Muhammad Hasnain Khan, Muhammad Hussain, Nooreen Zaki, Joma Mohammadi, Shayan Bali, Mohammad Javad Ranjbar, Els Lefever, and Veronique Hoste. 2026. APARSIN: A Multi-Variety Sentiment and Translation Benchmark for Iranic Languages. In The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family, pages 83–97, Rabat, Morocco. Association for Computational Linguistics.