@inproceedings{mokhtarabadi-etal-2026-computationally,
title = "Computationally Invisible: Charting the {NLP} Landscape of Iranic Languages",
author = "Mokhtarabadi, Hojjat and
Kargaran, Amir Hossein and
Shakeri, Ali and
Shafiei, Saba and
Nikeghbal, Nafiseh and
Manshaei, Mohammad Hossein",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2362/",
pages = "50767--50797",
ISBN = "979-8-89176-462-0",
abstract = "The Iranic language family spans 101 ISO 639-3 coded varieties and over 200 million speakers across a vast arc from the Caucasus through the Middle East and Central Asia to South Asia and China. Yet this richness is barely reflected in modern NLP: resources, models, and benchmarks are overwhelmingly concentrated on Iranian Persian, leaving Kurdish, Pashto, Balochi, Gilaki, Zazaki, and the Pamir languages computationally invisible. This survey provides the first comprehensive landscape analysis of Iranic NLP, covering 495 papers published between 2020 and early 2026. We examine language coverage, NLP tasks, datasets, modeling approaches, and evaluation practices, and identify persistent structural gaps: script heterogeneity, dialectal fragmentation, data scarcity, and an evaluation monoculture that has saturated Persian while leaving near-zero baselines for every other variety. Together with this survey, we release a companion website providing interactive language maps, a curated resource browser, and a live publication index at https://sigiranic.github.io."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mokhtarabadi-etal-2026-computationally">
<titleInfo>
<title>Computationally Invisible: Charting the NLP Landscape of Iranic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hojjat</namePart>
<namePart type="family">Mokhtarabadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="given">Hossein</namePart>
<namePart type="family">Kargaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Shakeri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saba</namePart>
<namePart type="family">Shafiei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nafiseh</namePart>
<namePart type="family">Nikeghbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Hossein</namePart>
<namePart type="family">Manshaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>The Iranic language family spans 101 ISO 639-3 coded varieties and over 200 million speakers across a vast arc from the Caucasus through the Middle East and Central Asia to South Asia and China. Yet this richness is barely reflected in modern NLP: resources, models, and benchmarks are overwhelmingly concentrated on Iranian Persian, leaving Kurdish, Pashto, Balochi, Gilaki, Zazaki, and the Pamir languages computationally invisible. This survey provides the first comprehensive landscape analysis of Iranic NLP, covering 495 papers published between 2020 and early 2026. We examine language coverage, NLP tasks, datasets, modeling approaches, and evaluation practices, and identify persistent structural gaps: script heterogeneity, dialectal fragmentation, data scarcity, and an evaluation monoculture that has saturated Persian while leaving near-zero baselines for every other variety. Together with this survey, we release a companion website providing interactive language maps, a curated resource browser, and a live publication index at https://sigiranic.github.io.</abstract>
<identifier type="citekey">mokhtarabadi-etal-2026-computationally</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2362/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>50767</start>
<end>50797</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Computationally Invisible: Charting the NLP Landscape of Iranic Languages
%A Mokhtarabadi, Hojjat
%A Kargaran, Amir Hossein
%A Shakeri, Ali
%A Shafiei, Saba
%A Nikeghbal, Nafiseh
%A Manshaei, Mohammad Hossein
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F mokhtarabadi-etal-2026-computationally
%X The Iranic language family spans 101 ISO 639-3 coded varieties and over 200 million speakers across a vast arc from the Caucasus through the Middle East and Central Asia to South Asia and China. Yet this richness is barely reflected in modern NLP: resources, models, and benchmarks are overwhelmingly concentrated on Iranian Persian, leaving Kurdish, Pashto, Balochi, Gilaki, Zazaki, and the Pamir languages computationally invisible. This survey provides the first comprehensive landscape analysis of Iranic NLP, covering 495 papers published between 2020 and early 2026. We examine language coverage, NLP tasks, datasets, modeling approaches, and evaluation practices, and identify persistent structural gaps: script heterogeneity, dialectal fragmentation, data scarcity, and an evaluation monoculture that has saturated Persian while leaving near-zero baselines for every other variety. Together with this survey, we release a companion website providing interactive language maps, a curated resource browser, and a live publication index at https://sigiranic.github.io.
%U https://aclanthology.org/2026.findings-emnlp.2362/
%P 50767-50797
Markdown (Informal)
[Computationally Invisible: Charting the NLP Landscape of Iranic Languages](https://aclanthology.org/2026.findings-emnlp.2362/) (Mokhtarabadi et al., Findings 2026)
ACL