@inproceedings{farsi-etal-2025-pahgen,
title = "{P}ah{G}en: Generating {A}ncient {P}ahlavi Text via Grammar-guided Zero-shot Translation",
author = "Farsi, Farhan and
Fazel, Parnian and
Goshtasb, Farzaneh and
Hajipour, Nadia and
Sabouri, Sadra and
Asgari, Ehsaneddin and
Sameti, Hossein",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Washington, Jonathan and
Oco, Nathaniel and
Zhao, Xiaobing",
booktitle = "Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico, U.S.A.",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loresmt-1.16/",
doi = "10.18653/v1/2025.loresmt-1.16",
pages = "171--182",
ISBN = "979-8-89176-230-5",
abstract = "The Pahlavi language, aka Middle Persian, is a critical part of Persian cultural and historical heritage which bridges the Old Persian and Modern Persian (Farsi). However, due to its limited digital presence and the scarcity of comprehensive linguistic resources, Pahlavi is at risk of extinction. As an early attempt to preserve this language, this study introduces a framework to translate English text into Pahlavi. Our approach combines grammar-guided term extraction with zero-shot translation, leveraging large language models (LLMs) to generate syntactically and semantically accurate Pahlavi sentences.This framework aims to preserve the Pahlavi language and serves as a model for reviving other endangered languages with similar characteristics. Finally using our framework, we generate a novel dataset of 360 expert-validated parallel English-Pahlavi texts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="farsi-etal-2025-pahgen">
<titleInfo>
<title>PahGen: Generating Ancient Pahlavi Text via Grammar-guided Zero-shot Translation</title>
</titleInfo>
<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">Parnian</namePart>
<namePart type="family">Fazel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farzaneh</namePart>
<namePart type="family">Goshtasb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadia</namePart>
<namePart type="family">Hajipour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadra</namePart>
<namePart type="family">Sabouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsaneddin</namePart>
<namePart type="family">Asgari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hossein</namePart>
<namePart type="family">Sameti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico, U.S.A.</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-230-5</identifier>
</relatedItem>
<abstract>The Pahlavi language, aka Middle Persian, is a critical part of Persian cultural and historical heritage which bridges the Old Persian and Modern Persian (Farsi). However, due to its limited digital presence and the scarcity of comprehensive linguistic resources, Pahlavi is at risk of extinction. As an early attempt to preserve this language, this study introduces a framework to translate English text into Pahlavi. Our approach combines grammar-guided term extraction with zero-shot translation, leveraging large language models (LLMs) to generate syntactically and semantically accurate Pahlavi sentences.This framework aims to preserve the Pahlavi language and serves as a model for reviving other endangered languages with similar characteristics. Finally using our framework, we generate a novel dataset of 360 expert-validated parallel English-Pahlavi texts.</abstract>
<identifier type="citekey">farsi-etal-2025-pahgen</identifier>
<identifier type="doi">10.18653/v1/2025.loresmt-1.16</identifier>
<location>
<url>https://aclanthology.org/2025.loresmt-1.16/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>171</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PahGen: Generating Ancient Pahlavi Text via Grammar-guided Zero-shot Translation
%A Farsi, Farhan
%A Fazel, Parnian
%A Goshtasb, Farzaneh
%A Hajipour, Nadia
%A Sabouri, Sadra
%A Asgari, Ehsaneddin
%A Sameti, Hossein
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Zhao, Xiaobing
%S Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico, U.S.A.
%@ 979-8-89176-230-5
%F farsi-etal-2025-pahgen
%X The Pahlavi language, aka Middle Persian, is a critical part of Persian cultural and historical heritage which bridges the Old Persian and Modern Persian (Farsi). However, due to its limited digital presence and the scarcity of comprehensive linguistic resources, Pahlavi is at risk of extinction. As an early attempt to preserve this language, this study introduces a framework to translate English text into Pahlavi. Our approach combines grammar-guided term extraction with zero-shot translation, leveraging large language models (LLMs) to generate syntactically and semantically accurate Pahlavi sentences.This framework aims to preserve the Pahlavi language and serves as a model for reviving other endangered languages with similar characteristics. Finally using our framework, we generate a novel dataset of 360 expert-validated parallel English-Pahlavi texts.
%R 10.18653/v1/2025.loresmt-1.16
%U https://aclanthology.org/2025.loresmt-1.16/
%U https://doi.org/10.18653/v1/2025.loresmt-1.16
%P 171-182
Markdown (Informal)
[PahGen: Generating Ancient Pahlavi Text via Grammar-guided Zero-shot Translation](https://aclanthology.org/2025.loresmt-1.16/) (Farsi et al., LoResMT 2025)
ACL
- Farhan Farsi, Parnian Fazel, Farzaneh Goshtasb, Nadia Hajipour, Sadra Sabouri, Ehsaneddin Asgari, and Hossein Sameti. 2025. PahGen: Generating Ancient Pahlavi Text via Grammar-guided Zero-shot Translation. In Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025), pages 171–182, Albuquerque, New Mexico, U.S.A.. Association for Computational Linguistics.