September 24, 2019 Software Open Access

Ligeia Lugli

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3459219</identifier>
  <creators>
    <creator>
      <creatorName>Ligeia Lugli</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-0473-4290</nameIdentifier>
      <affiliation>King's College London</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Buddhist Sanskrit Segmenter</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <subjects>
    <subject>Buddhist Sanskrit</subject>
    <subject>Natural Language Processing</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2019-09-24</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Software"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3459219</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3459218</relatedIdentifier>
  </relatedIdentifiers>
  <version>1</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;This folder contains R code for a rule-based Buddhist Sanskrit Segmenter and Lemmatiser, as well as data necessary to use and evaluate the Segmenter and explanatory materials.&lt;/p&gt;

&lt;p&gt;The segmenter has been tested on&amp;nbsp;639 sentences from 13 Buddhist text (9 sūtras, 4 śāstra) and has been evaluated as achieving 97% accuracy.&lt;/p&gt;

&lt;p&gt;The code and materials contained in this folder have been developed as part of a Newton&amp;nbsp;International Fellowship at King&amp;#39;s College London, funded by the British Academy (NF161436)&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Contents&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;R code for segmentation, lemmatisation and evaluation (includes instructions to run code)&lt;/p&gt;

&lt;p&gt;powerpoint presentation with background and explanation of project&lt;/p&gt;

&lt;p&gt;Wordlists and Wordlists documentation&lt;/p&gt;

&lt;p&gt;ngrams and stems frequency tables necessary for segmentation&lt;/p&gt;

&lt;p&gt;gold standard set of manually segmented and stemmed sentences for evaluation&lt;/p&gt;

&lt;p&gt;set of raw sentences for evaluation&lt;/p&gt;

&lt;p&gt;evaluation of&amp;nbsp;Krisha et al. seq2seq segmenter on Buddhist sentences for reference purposes&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;

&lt;p&gt;This segmenter has been used to prepare the Sanskrit Corpus at DOI&amp;nbsp;10.5281/zenodo.3457822&lt;/p&gt;</description>
  </descriptions>
</resource>