{"id":55718,"identifier":"DVN/29374","persistentUrl":"https://doi.org/10.7910/DVN/29374","protocol":"doi","authority":"10.7910","separator":"/","publisher":"Harvard Dataverse","publicationDate":"2015-03-06","storageIdentifier":"file://10.7910/DVN/29374","datasetType":"dataset","datasetVersion":{"id":54553,"datasetId":55718,"datasetPersistentId":"doi:10.7910/DVN/29374","storageIdentifier":"file://10.7910/DVN/29374","versionNumber":1,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"DRAFT","deaccessionNote":"This is the generated model, property file, and classification results.","deaccessionLink":"","distributionDate":"2015","lastUpdateTime":"2015-03-06T15:47:52Z","releaseTime":"2015-03-05T19:00:00Z","createTime":"2015-03-06T15:34:20Z","publicationDate":"2015-03-06","citationDate":"2015-03-06","license":{"name":"CC0 1.0","uri":"http://creativecommons.org/publicdomain/zero/1.0","iconUri":"https://licensebuttons.net/p/zero/1.0/88x31.png","rightsIdentifier":"CC0-1.0","rightsIdentifierScheme":"SPDX","schemeUri":"https://spdx.org/licenses/","languageCode":"en"},"fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Stanford NLP Model Output for Biofuel Patent Classification"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Kessler, Jeff"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of California, Davis"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Jeff Kessler"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"jkessler@ucdavis.edu"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"This NLP model was generated using the Stanford NLP Classifier (available from: http://nlp.stanford.edu/software/classifier.shtml).  The model was trained using a random selection of 700 manually classified biofuel patents from 1976 through 2013, and validated against 300 manually classified biofuel patents on January 03, 2014.   Included are the classification results and associated patent numbers for both the manually trained patents, and for the automatically categorized patents."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2015-03"}}]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Biofuel Classifier"},"keywordVocabulary":{"typeName":"keywordVocabulary","multiple":false,"typeClass":"primitive","value":"NLP"}}]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Natural Language Processing"}}]},{"typeName":"distributor","multiple":true,"typeClass":"compound","value":[{"distributorName":{"typeName":"distributorName","multiple":false,"typeClass":"primitive","value":"Harvard Dataverse Network"},"distributorURL":{"typeName":"distributorURL","multiple":false,"typeClass":"primitive","value":"http://thedata.harvard.edu/dvn/"}}]},{"typeName":"distributionDate","multiple":false,"typeClass":"primitive","value":"2015"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2015-03-06"},{"typeName":"timePeriodCovered","multiple":true,"typeClass":"compound","value":[{"timePeriodCoveredStart":{"typeName":"timePeriodCoveredStart","multiple":false,"typeClass":"primitive","value":"1976"},"timePeriodCoveredEnd":{"typeName":"timePeriodCoveredEnd","multiple":false,"typeClass":"primitive","value":"2013"}}]}]},"geospatial":{"displayName":"Geospatial Metadata","name":"geospatial","fields":[{"typeName":"geographicCoverage","multiple":true,"typeClass":"compound","value":[{"otherGeographicCoverage":{"typeName":"otherGeographicCoverage","multiple":false,"typeClass":"primitive","value":"United States"}}]}]}},"files":[{"description":"This is the initial list of 1000 patents manually classified for use with training and validating the NLP model","label":"Manual Classification.csv","restricted":false,"version":1,"datasetVersionId":54553,"categories":["Manually classified patents"],"dataFile":{"id":2544481,"persistentId":"doi:10.7910/DVN/29374/NBV4LD","pidURL":"https://doi.org/10.7910/DVN/29374/NBV4LD","filename":"Manual Classification.csv","contentType":"text/plain; charset=US-ASCII","friendlyType":"Plain Text","filesize":15034,"description":"This is the initial list of 1000 patents manually classified for use with training and validating the NLP model","categories":["Manually classified patents"],"storageIdentifier":"s3://dvn-cloud:298584","rootDataFileId":-1,"md5":"9ad7db0ad4a0cc2009aa9f706c6a1949","checksum":{"type":"MD5","value":"9ad7db0ad4a0cc2009aa9f706c6a1949"},"tabularData":false,"creationDate":"2015-03-06","publicationDate":"2015-03-05","fileAccessRequest":false}},{"description":"This is the model generated by the Stanford NLP Classifier","label":"ner-model.ser.gz","restricted":false,"version":1,"datasetVersionId":54553,"categories":["Model"],"dataFile":{"id":2544475,"persistentId":"doi:10.7910/DVN/29374/FUSEA8","pidURL":"https://doi.org/10.7910/DVN/29374/FUSEA8","filename":"ner-model.ser.gz","contentType":"application/x-gzip","friendlyType":"Gzip Archive","filesize":4416022,"description":"This is the model generated by the Stanford NLP Classifier","categories":["Model"],"storageIdentifier":"s3://dvn-cloud:298570","rootDataFileId":-1,"md5":"a2646273d1b3b5718ed10135a3275c06","checksum":{"type":"MD5","value":"a2646273d1b3b5718ed10135a3275c06"},"tabularData":false,"creationDate":"2015-03-06","publicationDate":"2015-03-05","fileAccessRequest":false}},{"description":"This is the list of patents and associated classifications based on the NLP model that was trained using the manually classified patents","label":"NLP Classification.csv","restricted":false,"version":1,"datasetVersionId":54553,"categories":["NLP Classified patents"],"dataFile":{"id":2544480,"persistentId":"doi:10.7910/DVN/29374/EBPLPU","pidURL":"https://doi.org/10.7910/DVN/29374/EBPLPU","filename":"NLP Classification.csv","contentType":"text/plain; charset=US-ASCII","friendlyType":"Plain Text","filesize":18219545,"description":"This is the list of patents and associated classifications based on the NLP model that was trained using the manually classified patents","categories":["NLP Classified patents"],"storageIdentifier":"s3://dvn-cloud:298585","rootDataFileId":-1,"md5":"f57c572506c64a4ceb2c2ffeeb8f9396","checksum":{"type":"MD5","value":"f57c572506c64a4ceb2c2ffeeb8f9396"},"tabularData":false,"creationDate":"2015-03-06","publicationDate":"2015-03-05","fileAccessRequest":false}},{"description":"This is the property file used for parameterizing the model","label":"patents_test.prop","restricted":false,"version":1,"datasetVersionId":54553,"categories":["Model Parameters"],"dataFile":{"id":2544476,"persistentId":"doi:10.7910/DVN/29374/OVGOAU","pidURL":"https://doi.org/10.7910/DVN/29374/OVGOAU","filename":"patents_test.prop","contentType":"text/plain; charset=US-ASCII","friendlyType":"Plain Text","filesize":984,"description":"This is the property file used for parameterizing the model","categories":["Model Parameters"],"storageIdentifier":"s3://dvn-cloud:298571","rootDataFileId":-1,"md5":"b09711539fd182bb2bbd76608141b133","checksum":{"type":"MD5","value":"b09711539fd182bb2bbd76608141b133"},"tabularData":false,"creationDate":"2015-03-06","publicationDate":"2015-03-05","fileAccessRequest":false}}],"citation":"Kessler, Jeff, 2015, \"Stanford NLP Model Output for Biofuel Patent Classification\", https://doi.org/10.7910/DVN/29374, Harvard Dataverse, V1"}}