Software Open Access
<?xml version='1.0' encoding='utf-8'?> <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#"> <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.3459219"> <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/> <dct:type rdf:resource="http://purl.org/dc/dcmitype/Software"/> <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.3459219</dct:identifier> <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dct:creator> <rdf:Description rdf:about="http://orcid.org/0000-0003-0473-4290"> <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/> <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-0473-4290</dct:identifier> <foaf:name>Ligeia Lugli</foaf:name> <org:memberOf> <foaf:Organization> <foaf:name>King's College London</foaf:name> </foaf:Organization> </org:memberOf> </rdf:Description> </dct:creator> <dct:title>Buddhist Sanskrit Segmenter</dct:title> <dct:publisher> <foaf:Agent> <foaf:name>Zenodo</foaf:name> </foaf:Agent> </dct:publisher> <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2019</dct:issued> <dcat:keyword>Buddhist Sanskrit</dcat:keyword> <dcat:keyword>Natural Language Processing</dcat:keyword> <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2019-09-24</dct:issued> <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/> <owl:sameAs rdf:resource="https://zenodo.org/record/3459219"/> <adms:identifier> <adms:Identifier> <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3459219</skos:notation> <adms:schemeAgency>url</adms:schemeAgency> </adms:Identifier> </adms:identifier> <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3459218"/> <owl:versionInfo>1</owl:versionInfo> <dct:description><p>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.</p> <p>The segmenter has been tested on&nbsp;639 sentences from 13 Buddhist text (9 sūtras, 4 śāstra) and has been evaluated as achieving 97% accuracy.</p> <p>The code and materials contained in this folder have been developed as part of a Newton&nbsp;International Fellowship at King&#39;s College London, funded by the British Academy (NF161436)</p> <p>&nbsp;</p> <p><strong>Contents</strong></p> <p>R code for segmentation, lemmatisation and evaluation (includes instructions to run code)</p> <p>powerpoint presentation with background and explanation of project</p> <p>Wordlists and Wordlists documentation</p> <p>ngrams and stems frequency tables necessary for segmentation</p> <p>gold standard set of manually segmented and stemmed sentences for evaluation</p> <p>set of raw sentences for evaluation</p> <p>evaluation of&nbsp;Krisha et al. seq2seq segmenter on Buddhist sentences for reference purposes</p> <p>&nbsp;</p> <p>This segmenter has been used to prepare the Sanskrit Corpus at DOI&nbsp;10.5281/zenodo.3457822</p></dct:description> <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/> <dct:accessRights> <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess"> <rdfs:label>Open Access</rdfs:label> </dct:RightsStatement> </dct:accessRights> <dcat:distribution> <dcat:Distribution> <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>192850</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_BuddhFoundCorpusNgramsRedux.csv"/> <dcat:mediaType>text/csv</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>244573</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_BuddhSktSegmenterLemmatiser2019.R"/> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>9160483</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_CL2019_BuddhistSanskritSegmenterPresentation.pptx"/> <dcat:mediaType>application/vnd.openxmlformats-officedocument.presentationml.presentation</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>212507</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_FiveTextsSegmentedTokensDFWithCleanFreq.csv"/> <dcat:mediaType>text/csv</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>473717</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_GretilBuddhRelLit_NgramsRedux.csv"/> <dcat:mediaType>text/csv</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>311888</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_GretilBuddhSastraSastra_NgramsRedux.csv"/> <dcat:mediaType>text/csv</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>3037610</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_NonStemmedWordlist.csv"/> <dcat:mediaType>text/csv</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>75297</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_Segmenter_Eva_AllGoldSent.csv"/> <dcat:mediaType>text/csv</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>34650</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_SegmenterEva_RawOneSentencePerLine.zip"/> <dcat:mediaType>application/zip</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>1105346</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_WordlistNoA_June2019.csv"/> <dcat:mediaType>text/csv</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>62929</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Lugli_Wordlist_ReadMe.html"/> <dcat:mediaType>text/html</dcat:mediaType> </dcat:Distribution> </dcat:distribution> <dcat:distribution> <dcat:Distribution> <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3459219"/> <dcat:byteSize>25325</dcat:byteSize> <dcat:downloadURL rdf:resource="https://zenodo.org/record/3459219/files/Seq2Seq_segmentertest-full-vocabulary_GeoffroyNoel.txt"/> <dcat:mediaType>text/plain</dcat:mediaType> </dcat:Distribution> </dcat:distribution> </rdf:Description> </rdf:RDF>
All versions | This version | |
---|---|---|
Views | 111 | 33 |
Downloads | 557 | 463 |
Data volume | 577.2 MB | 383.3 MB |
Unique views | 101 | 30 |
Unique downloads | 448 | 406 |