@inproceedings{tsukagoshi-ohmukai-2024-n,
title = "N-gram-Based Preprocessing for Sandhi Reversion in {V}edic {S}anskrit",
author = "Tsukagoshi, Yuzuki and
Ohmukai, Ikki",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Miyagawa, So and
Alnajjar, Khalid and
Bizzoni, Yuri},
booktitle = "Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities",
month = nov,
year = "2024",
address = "Miami, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlp4dh-1.26",
pages = "275--279",
abstract = "This study aims to address the challenges posed by sandhi in Vedic Sanskrit, a phenomenon that complicates the computational analysis of Sanskrit texts. By focusing on sandhi reversion, the research seeks to improve the accuracy of processing Vedic Sanskrit, an older layer of the language. Sandhi, a phonological phenomenon, poses challenges for text processing in Sanskrit due to the fusion of word boundaries or the sound change around word boundaries. In this research, we developed a transformer-based model with a novel n-gram preprocessing strategy to improve the accuracy of sandhi reversion for Vedic. We created character-based n-gram texts of varying lengths (n = 2, 3, 4, 5, 6) from the Rigveda, the oldest Vedic text, and trained models on these texts to perform machine translation from post-sandhi to pre-sandhi forms. In the results, we found that the model trained with 5-gram text achieved the highest accuracy. This success is likely due to the 5-gram{'}s ability to capture the maximum phonemic context in which Vedic sandhi occurs, making it more effective for the task. These findings suggest that by leveraging the inherent characteristics of phonological changes in language, even simple preprocessing methods like n-gram segmentation can significantly improve the accuracy of complex linguistic tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsukagoshi-ohmukai-2024-n">
<titleInfo>
<title>N-gram-Based Preprocessing for Sandhi Reversion in Vedic Sanskrit</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuzuki</namePart>
<namePart type="family">Tsukagoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ikki</namePart>
<namePart type="family">Ohmukai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study aims to address the challenges posed by sandhi in Vedic Sanskrit, a phenomenon that complicates the computational analysis of Sanskrit texts. By focusing on sandhi reversion, the research seeks to improve the accuracy of processing Vedic Sanskrit, an older layer of the language. Sandhi, a phonological phenomenon, poses challenges for text processing in Sanskrit due to the fusion of word boundaries or the sound change around word boundaries. In this research, we developed a transformer-based model with a novel n-gram preprocessing strategy to improve the accuracy of sandhi reversion for Vedic. We created character-based n-gram texts of varying lengths (n = 2, 3, 4, 5, 6) from the Rigveda, the oldest Vedic text, and trained models on these texts to perform machine translation from post-sandhi to pre-sandhi forms. In the results, we found that the model trained with 5-gram text achieved the highest accuracy. This success is likely due to the 5-gram’s ability to capture the maximum phonemic context in which Vedic sandhi occurs, making it more effective for the task. These findings suggest that by leveraging the inherent characteristics of phonological changes in language, even simple preprocessing methods like n-gram segmentation can significantly improve the accuracy of complex linguistic tasks.</abstract>
<identifier type="citekey">tsukagoshi-ohmukai-2024-n</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4dh-1.26</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>275</start>
<end>279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T N-gram-Based Preprocessing for Sandhi Reversion in Vedic Sanskrit
%A Tsukagoshi, Yuzuki
%A Ohmukai, Ikki
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Miyagawa, So
%Y Alnajjar, Khalid
%Y Bizzoni, Yuri
%S Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, USA
%F tsukagoshi-ohmukai-2024-n
%X This study aims to address the challenges posed by sandhi in Vedic Sanskrit, a phenomenon that complicates the computational analysis of Sanskrit texts. By focusing on sandhi reversion, the research seeks to improve the accuracy of processing Vedic Sanskrit, an older layer of the language. Sandhi, a phonological phenomenon, poses challenges for text processing in Sanskrit due to the fusion of word boundaries or the sound change around word boundaries. In this research, we developed a transformer-based model with a novel n-gram preprocessing strategy to improve the accuracy of sandhi reversion for Vedic. We created character-based n-gram texts of varying lengths (n = 2, 3, 4, 5, 6) from the Rigveda, the oldest Vedic text, and trained models on these texts to perform machine translation from post-sandhi to pre-sandhi forms. In the results, we found that the model trained with 5-gram text achieved the highest accuracy. This success is likely due to the 5-gram’s ability to capture the maximum phonemic context in which Vedic sandhi occurs, making it more effective for the task. These findings suggest that by leveraging the inherent characteristics of phonological changes in language, even simple preprocessing methods like n-gram segmentation can significantly improve the accuracy of complex linguistic tasks.
%U https://aclanthology.org/2024.nlp4dh-1.26
%P 275-279
Markdown (Informal)
[N-gram-Based Preprocessing for Sandhi Reversion in Vedic Sanskrit](https://aclanthology.org/2024.nlp4dh-1.26) (Tsukagoshi & Ohmukai, NLP4DH 2024)
ACL