@inproceedings{farsi-etal-2025-parsipy,
title = "{P}arsi{P}y: {NLP} Toolkit for Historical {P}ersian Texts in Python",
author = "Farsi, Farhan and
Fazel, Parnian and
Haghighi, Sepand and
Sabouri, Sadra and
Goshtasb, Farzaneh and
Hajipour, Nadia and
Asgari, Ehsaneddin and
Sameti, Hossein",
editor = "Anderson, Adam and
Gordin, Shai and
Li, Bin and
Liu, Yudong and
Passarotti, Marco C. and
Sprugnoli, Rachele",
booktitle = "Proceedings of the Second Workshop on Ancient Language Processing",
month = may,
year = "2025",
address = "The Albuquerque Convention Center, Laguna",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.alp-1.17/",
doi = "10.18653/v1/2025.alp-1.17",
pages = "137--149",
ISBN = "979-8-89176-235-0",
abstract = "The study of historical languages presents unique challenges due to their complex ortho-graphic systems, fragmentary textual evidence, and the absence of standardized digital repre-sentations of text in those languages. Tack-ling these challenges needs special NLP digi-tal tools to handle phonetic transcriptions and analyze ancient texts. This work introduces ParsiPy1, an NLP toolkit designed to facili-tate the analysis of historical Persian languages by offering modules for tokenization, lemma-tization, part-of-speech tagging, phoneme-to-transliteration conversion, and word embed-ding. We demonstrate the utility of our toolkit through the processing of Parsig (Middle Per-sian) texts, highlighting its potential for ex-panding computational methods in the study of historical languages. Through this work, we contribute to the field of computational philol-ogy, offering tools that can be adapted for the broader study of ancient texts and their digital preservation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="farsi-etal-2025-parsipy">
<titleInfo>
<title>ParsiPy: NLP Toolkit for Historical Persian Texts in Python</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">Sepand</namePart>
<namePart type="family">Haghighi</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">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">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 Second Workshop on Ancient Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">The Albuquerque Convention Center, Laguna</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-235-0</identifier>
</relatedItem>
<abstract>The study of historical languages presents unique challenges due to their complex ortho-graphic systems, fragmentary textual evidence, and the absence of standardized digital repre-sentations of text in those languages. Tack-ling these challenges needs special NLP digi-tal tools to handle phonetic transcriptions and analyze ancient texts. This work introduces ParsiPy1, an NLP toolkit designed to facili-tate the analysis of historical Persian languages by offering modules for tokenization, lemma-tization, part-of-speech tagging, phoneme-to-transliteration conversion, and word embed-ding. We demonstrate the utility of our toolkit through the processing of Parsig (Middle Per-sian) texts, highlighting its potential for ex-panding computational methods in the study of historical languages. Through this work, we contribute to the field of computational philol-ogy, offering tools that can be adapted for the broader study of ancient texts and their digital preservation.</abstract>
<identifier type="citekey">farsi-etal-2025-parsipy</identifier>
<identifier type="doi">10.18653/v1/2025.alp-1.17</identifier>
<location>
<url>https://aclanthology.org/2025.alp-1.17/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>137</start>
<end>149</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParsiPy: NLP Toolkit for Historical Persian Texts in Python
%A Farsi, Farhan
%A Fazel, Parnian
%A Haghighi, Sepand
%A Sabouri, Sadra
%A Goshtasb, Farzaneh
%A Hajipour, Nadia
%A Asgari, Ehsaneddin
%A Sameti, Hossein
%Y Anderson, Adam
%Y Gordin, Shai
%Y Li, Bin
%Y Liu, Yudong
%Y Passarotti, Marco C.
%Y Sprugnoli, Rachele
%S Proceedings of the Second Workshop on Ancient Language Processing
%D 2025
%8 May
%I Association for Computational Linguistics
%C The Albuquerque Convention Center, Laguna
%@ 979-8-89176-235-0
%F farsi-etal-2025-parsipy
%X The study of historical languages presents unique challenges due to their complex ortho-graphic systems, fragmentary textual evidence, and the absence of standardized digital repre-sentations of text in those languages. Tack-ling these challenges needs special NLP digi-tal tools to handle phonetic transcriptions and analyze ancient texts. This work introduces ParsiPy1, an NLP toolkit designed to facili-tate the analysis of historical Persian languages by offering modules for tokenization, lemma-tization, part-of-speech tagging, phoneme-to-transliteration conversion, and word embed-ding. We demonstrate the utility of our toolkit through the processing of Parsig (Middle Per-sian) texts, highlighting its potential for ex-panding computational methods in the study of historical languages. Through this work, we contribute to the field of computational philol-ogy, offering tools that can be adapted for the broader study of ancient texts and their digital preservation.
%R 10.18653/v1/2025.alp-1.17
%U https://aclanthology.org/2025.alp-1.17/
%U https://doi.org/10.18653/v1/2025.alp-1.17
%P 137-149
Markdown (Informal)
[ParsiPy: NLP Toolkit for Historical Persian Texts in Python](https://aclanthology.org/2025.alp-1.17/) (Farsi et al., ALP 2025)
ACL
- Farhan Farsi, Parnian Fazel, Sepand Haghighi, Sadra Sabouri, Farzaneh Goshtasb, Nadia Hajipour, Ehsaneddin Asgari, and Hossein Sameti. 2025. ParsiPy: NLP Toolkit for Historical Persian Texts in Python. In Proceedings of the Second Workshop on Ancient Language Processing, pages 137–149, The Albuquerque Convention Center, Laguna. Association for Computational Linguistics.