@inproceedings{krishnan-kulkarni-2019-sanskrit,
title = "{S}anskrit Segmentation revisited",
author = "Krishnan, Sriram and
Kulkarni, Amba",
editor = "Sharma, Dipti Misra and
Bhattacharya, Pushpak",
booktitle = "Proceedings of the 16th International Conference on Natural Language Processing",
month = dec,
year = "2019",
address = "International Institute of Information Technology, Hyderabad, India",
publisher = "NLP Association of India",
url = "https://aclanthology.org/2019.icon-1.12",
pages = "105--114",
abstract = "Computationally analyzing Sanskrit texts requires proper segmentation in the initial stages. There have been various tools developed for Sanskrit text segmentation. Of these, G{\'e}rard Huet{'}s Reader in the Sanskrit Heritage Engine analyzes the input text and segments it based on the word parameters - phases like iic, ifc, Pr, Subst, etc., and sandhi (or transition) that takes place at the end of a word with the initial part of the next word. And it enlists all the possible solutions differentiating them with the help of the phases. The phases and their analyses have their use in the domain of sentential parsers. In segmentation, though, they are not used beyond deciding whether the words formed with the phases are morphologically valid. This paper tries to modify the above segmenter by ignoring the phase details (except for a few cases), and also proposes a probability function to prioritize the list of solutions to bring up the most valid solutions at the top.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishnan-kulkarni-2019-sanskrit">
<titleInfo>
<title>Sanskrit Segmentation revisited</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sriram</namePart>
<namePart type="family">Krishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amba</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India</publisher>
<place>
<placeTerm type="text">International Institute of Information Technology, Hyderabad, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Computationally analyzing Sanskrit texts requires proper segmentation in the initial stages. There have been various tools developed for Sanskrit text segmentation. Of these, Gérard Huet’s Reader in the Sanskrit Heritage Engine analyzes the input text and segments it based on the word parameters - phases like iic, ifc, Pr, Subst, etc., and sandhi (or transition) that takes place at the end of a word with the initial part of the next word. And it enlists all the possible solutions differentiating them with the help of the phases. The phases and their analyses have their use in the domain of sentential parsers. In segmentation, though, they are not used beyond deciding whether the words formed with the phases are morphologically valid. This paper tries to modify the above segmenter by ignoring the phase details (except for a few cases), and also proposes a probability function to prioritize the list of solutions to bring up the most valid solutions at the top.</abstract>
<identifier type="citekey">krishnan-kulkarni-2019-sanskrit</identifier>
<location>
<url>https://aclanthology.org/2019.icon-1.12</url>
</location>
<part>
<date>2019-12</date>
<extent unit="page">
<start>105</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sanskrit Segmentation revisited
%A Krishnan, Sriram
%A Kulkarni, Amba
%Y Sharma, Dipti Misra
%Y Bhattacharya, Pushpak
%S Proceedings of the 16th International Conference on Natural Language Processing
%D 2019
%8 December
%I NLP Association of India
%C International Institute of Information Technology, Hyderabad, India
%F krishnan-kulkarni-2019-sanskrit
%X Computationally analyzing Sanskrit texts requires proper segmentation in the initial stages. There have been various tools developed for Sanskrit text segmentation. Of these, Gérard Huet’s Reader in the Sanskrit Heritage Engine analyzes the input text and segments it based on the word parameters - phases like iic, ifc, Pr, Subst, etc., and sandhi (or transition) that takes place at the end of a word with the initial part of the next word. And it enlists all the possible solutions differentiating them with the help of the phases. The phases and their analyses have their use in the domain of sentential parsers. In segmentation, though, they are not used beyond deciding whether the words formed with the phases are morphologically valid. This paper tries to modify the above segmenter by ignoring the phase details (except for a few cases), and also proposes a probability function to prioritize the list of solutions to bring up the most valid solutions at the top.
%U https://aclanthology.org/2019.icon-1.12
%P 105-114
Markdown (Informal)
[Sanskrit Segmentation revisited](https://aclanthology.org/2019.icon-1.12) (Krishnan & Kulkarni, ICON 2019)
ACL
- Sriram Krishnan and Amba Kulkarni. 2019. Sanskrit Segmentation revisited. In Proceedings of the 16th International Conference on Natural Language Processing, pages 105–114, International Institute of Information Technology, Hyderabad, India. NLP Association of India.