@inproceedings{de-luca-etal-2025-sanskrit,
title = "{S}anskrit Voyager: Unified Web Platform for Interactive Reading and Linguistic Analysis of {S}anskrit Texts",
author = "De Luca, Giacomo and
Croce, Danilo and
Basili, Roberto",
editor = {Habernal, Ivan and
Schulam, Peter and
Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-demos.18/",
pages = "244--253",
ISBN = "979-8-89176-334-0",
abstract = "Sanskrit Voyager is a web application for searching, reading, and analyzing the texts in the Sanskrit literary corpus. Unlike previous tools that require expert linguistic knowledge or manual normalization, Sanskrit Voyager enables users to search for words and phrases as they actually appear in texts, handling inflection, sandhi, and compound forms automatically while supporting any transliteration. The system integrates four core functionalities: (1) multi-dictionary lookup with morphological analysis and inflection tables; (2) real-time text parsing and annotation; (3) an interactive reader for over 900 digitalized texts; and (4) advanced corpus search with fuzzy matching and filtering. Evaluation shows over 92{\%} parsing accuracy on complex compounds and substantially higher search recall than BuddhaNexus on challenging queries. Source code is publicly available under CC-BY-NC license, resource-efficient, and designed for both learners and researchers, offering the first fully integrated, user-friendly platform for computational Sanskrit studies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-luca-etal-2025-sanskrit">
<titleInfo>
<title>Sanskrit Voyager: Unified Web Platform for Interactive Reading and Linguistic Analysis of Sanskrit Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giacomo</namePart>
<namePart type="family">De Luca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Croce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Basili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Habernal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Schulam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-334-0</identifier>
</relatedItem>
<abstract>Sanskrit Voyager is a web application for searching, reading, and analyzing the texts in the Sanskrit literary corpus. Unlike previous tools that require expert linguistic knowledge or manual normalization, Sanskrit Voyager enables users to search for words and phrases as they actually appear in texts, handling inflection, sandhi, and compound forms automatically while supporting any transliteration. The system integrates four core functionalities: (1) multi-dictionary lookup with morphological analysis and inflection tables; (2) real-time text parsing and annotation; (3) an interactive reader for over 900 digitalized texts; and (4) advanced corpus search with fuzzy matching and filtering. Evaluation shows over 92% parsing accuracy on complex compounds and substantially higher search recall than BuddhaNexus on challenging queries. Source code is publicly available under CC-BY-NC license, resource-efficient, and designed for both learners and researchers, offering the first fully integrated, user-friendly platform for computational Sanskrit studies.</abstract>
<identifier type="citekey">de-luca-etal-2025-sanskrit</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-demos.18/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>244</start>
<end>253</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sanskrit Voyager: Unified Web Platform for Interactive Reading and Linguistic Analysis of Sanskrit Texts
%A De Luca, Giacomo
%A Croce, Danilo
%A Basili, Roberto
%Y Habernal, Ivan
%Y Schulam, Peter
%Y Tiedemann, Jörg
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-334-0
%F de-luca-etal-2025-sanskrit
%X Sanskrit Voyager is a web application for searching, reading, and analyzing the texts in the Sanskrit literary corpus. Unlike previous tools that require expert linguistic knowledge or manual normalization, Sanskrit Voyager enables users to search for words and phrases as they actually appear in texts, handling inflection, sandhi, and compound forms automatically while supporting any transliteration. The system integrates four core functionalities: (1) multi-dictionary lookup with morphological analysis and inflection tables; (2) real-time text parsing and annotation; (3) an interactive reader for over 900 digitalized texts; and (4) advanced corpus search with fuzzy matching and filtering. Evaluation shows over 92% parsing accuracy on complex compounds and substantially higher search recall than BuddhaNexus on challenging queries. Source code is publicly available under CC-BY-NC license, resource-efficient, and designed for both learners and researchers, offering the first fully integrated, user-friendly platform for computational Sanskrit studies.
%U https://aclanthology.org/2025.emnlp-demos.18/
%P 244-253
Markdown (Informal)
[Sanskrit Voyager: Unified Web Platform for Interactive Reading and Linguistic Analysis of Sanskrit Texts](https://aclanthology.org/2025.emnlp-demos.18/) (De Luca et al., EMNLP 2025)
ACL