@inproceedings{rahnamoun-rahnamoun-2025-semantic,
title = "Semantic Analysis of Jurisprudential Zoroastrian Texts in {P}ahlavi: A Word Embedding Approach for an Extremely Under-Resourced, Extinct Language",
author = "Rahnamoun, Rashin and
Rahnamoun, Ramin",
editor = "Yagi, Sane and
Yagi, Sane and
Sawalha, Majdi and
Shawar, Bayan Abu and
AlShdaifat, Abdallah T. and
Abbas, Norhan and
Organizers",
booktitle = "Proceedings of the New Horizons in Computational Linguistics for Religious Texts",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.clrel-1.3/",
pages = "23--41",
abstract = "Zoroastrianism, one of the earliest known religions, reached its height of influence during the Sassanian period, embedding itself within the governmental structure before the rise of Islam in the 7th century led to a significant shift. Subsequently, a substantial body of Zoroastrian literature in Middle Persian (Pahlavi) emerged, primarily addressing religious, ethical, and legal topics and reflecting Zoroastrian responses to evolving Islamic jurisprudence. The text {\v{S}}{\={a}}yist n{\={e}} {\v{s}}{\={a}}yist (Licit and Illicit), which is central to this study, provides guidance on purity and pollution, offering insights into Zoroastrian legal principles during the late Sassanian period. This study marks the first known application of machine processing to Book Pahlavi texts, focusing on a jurisprudential Zoroastrian text. A Pahlavi corpus was compiled, and word embedding techniques were applied to uncover semantic relationships within the selected text. Given the lack of digital resources and data standards for Pahlavi, a unique dataset of vocabulary pairs was created for evaluating embedding models, allowing for the selection of optimal methods and hyperparameter settings. By constructing a complex network using these embeddings, and leveraging the scarcity of texts in this field, we used complex network analysis to extract additional information about the features of the text. We applied this approach to the chapters of the {\v{S}}{\={a}}yist n{\={e}} {\v{s}}{\={a}}yist book, uncovering more insights from each chapter. This approach facilitated the initial semantic analysis of Pahlavi legal concepts, contributing to the computational exploration of Middle Persian religious literature."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahnamoun-rahnamoun-2025-semantic">
<titleInfo>
<title>Semantic Analysis of Jurisprudential Zoroastrian Texts in Pahlavi: A Word Embedding Approach for an Extremely Under-Resourced, Extinct Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rashin</namePart>
<namePart type="family">Rahnamoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramin</namePart>
<namePart type="family">Rahnamoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the New Horizons in Computational Linguistics for Religious Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sane</namePart>
<namePart type="family">Yagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majdi</namePart>
<namePart type="family">Sawalha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bayan</namePart>
<namePart type="given">Abu</namePart>
<namePart type="family">Shawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdallah</namePart>
<namePart type="given">T</namePart>
<namePart type="family">AlShdaifat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norhan</namePart>
<namePart type="family">Abbas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name>
<namePart>Organizers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Zoroastrianism, one of the earliest known religions, reached its height of influence during the Sassanian period, embedding itself within the governmental structure before the rise of Islam in the 7th century led to a significant shift. Subsequently, a substantial body of Zoroastrian literature in Middle Persian (Pahlavi) emerged, primarily addressing religious, ethical, and legal topics and reflecting Zoroastrian responses to evolving Islamic jurisprudence. The text Šāyist nē šāyist (Licit and Illicit), which is central to this study, provides guidance on purity and pollution, offering insights into Zoroastrian legal principles during the late Sassanian period. This study marks the first known application of machine processing to Book Pahlavi texts, focusing on a jurisprudential Zoroastrian text. A Pahlavi corpus was compiled, and word embedding techniques were applied to uncover semantic relationships within the selected text. Given the lack of digital resources and data standards for Pahlavi, a unique dataset of vocabulary pairs was created for evaluating embedding models, allowing for the selection of optimal methods and hyperparameter settings. By constructing a complex network using these embeddings, and leveraging the scarcity of texts in this field, we used complex network analysis to extract additional information about the features of the text. We applied this approach to the chapters of the Šāyist nē šāyist book, uncovering more insights from each chapter. This approach facilitated the initial semantic analysis of Pahlavi legal concepts, contributing to the computational exploration of Middle Persian religious literature.</abstract>
<identifier type="citekey">rahnamoun-rahnamoun-2025-semantic</identifier>
<location>
<url>https://aclanthology.org/2025.clrel-1.3/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>23</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Analysis of Jurisprudential Zoroastrian Texts in Pahlavi: A Word Embedding Approach for an Extremely Under-Resourced, Extinct Language
%A Rahnamoun, Rashin
%A Rahnamoun, Ramin
%Y Yagi, Sane
%Y Sawalha, Majdi
%Y Shawar, Bayan Abu
%Y AlShdaifat, Abdallah T.
%Y Abbas, Norhan
%E Organizers
%S Proceedings of the New Horizons in Computational Linguistics for Religious Texts
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F rahnamoun-rahnamoun-2025-semantic
%X Zoroastrianism, one of the earliest known religions, reached its height of influence during the Sassanian period, embedding itself within the governmental structure before the rise of Islam in the 7th century led to a significant shift. Subsequently, a substantial body of Zoroastrian literature in Middle Persian (Pahlavi) emerged, primarily addressing religious, ethical, and legal topics and reflecting Zoroastrian responses to evolving Islamic jurisprudence. The text Šāyist nē šāyist (Licit and Illicit), which is central to this study, provides guidance on purity and pollution, offering insights into Zoroastrian legal principles during the late Sassanian period. This study marks the first known application of machine processing to Book Pahlavi texts, focusing on a jurisprudential Zoroastrian text. A Pahlavi corpus was compiled, and word embedding techniques were applied to uncover semantic relationships within the selected text. Given the lack of digital resources and data standards for Pahlavi, a unique dataset of vocabulary pairs was created for evaluating embedding models, allowing for the selection of optimal methods and hyperparameter settings. By constructing a complex network using these embeddings, and leveraging the scarcity of texts in this field, we used complex network analysis to extract additional information about the features of the text. We applied this approach to the chapters of the Šāyist nē šāyist book, uncovering more insights from each chapter. This approach facilitated the initial semantic analysis of Pahlavi legal concepts, contributing to the computational exploration of Middle Persian religious literature.
%U https://aclanthology.org/2025.clrel-1.3/
%P 23-41
Markdown (Informal)
[Semantic Analysis of Jurisprudential Zoroastrian Texts in Pahlavi: A Word Embedding Approach for an Extremely Under-Resourced, Extinct Language](https://aclanthology.org/2025.clrel-1.3/) (Rahnamoun & Rahnamoun, CLRel 2025)
ACL