{"status":"OK","data":{"id":452781,"identifier":"D9AKUS","persistentUrl":"https://doi.org/10.34894/D9AKUS","protocol":"doi","authority":"10.34894","separator":"/","publisher":"DataverseNL","publicationDate":"2024-12-17","storageIdentifier":"surf://10.34894/D9AKUS","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9995,"datasetType":"dataset","locks":[],"latestVersion":{"id":29740,"datasetId":452781,"datasetPersistentId":"doi:10.34894/D9AKUS","datasetType":"dataset","storageIdentifier":"surf://10.34894/D9AKUS","versionNumber":1,"internalVersionNumber":17,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","deaccessionLink":"","productionDate":"2023-09-01","lastUpdateTime":"2024-12-17T14:04:00Z","releaseTime":"2024-12-17T14:04:00Z","createTime":"2024-10-01T21:03:08Z","publicationDate":"2024-12-17","citationDate":"2024-12-17","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9995,"license":{"name":"CC-BY-4.0","uri":"http://creativecommons.org/licenses/by/4.0","iconUri":"https://i.creativecommons.org/l/by/4.0/88x31.png"},"sizeOfCollection":"2","fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"To NER or not to NER? A case study of low-resource deontic modalities in EU legislation?"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Chakravarthy, Shashank"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/02jz4aj89","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"Maastricht University","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0003-3336-8402"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Dijck, Gijs van"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/02jz4aj89","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"Maastricht University","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0003-4102-4415"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Wilbik, Anna"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/02jz4aj89","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"Maastricht University","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0002-1989-0301"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Chakravarthy, Shashank"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"maastrichtuniversity.nl"}},{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Dijck, Gijs van"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"Deontic modality (obligation, permission, prohibition) in legal documents can convey critical information, and identification of deontic modalities is often performed using Natural Language Processing (NLP) techniques as a `Deontic Modality Classification' (DMC) text classification task. As deontic modalities in legal text are not mutually exclusive, a key challenge with DMC is that it classifies the provided text into a single modality while in reality it might have multiple deontic modalities. To address this, this study analyzes the feasibility of performing deontic modality identification as a Named Entity Recognition (NER) task over DMC task approaches in a low-resource data setting with EU legislation. \nLow-resource NLP approaches can offer solutions to tackle the problem of scarce data. In this paper, we use a rule-based approach with modal verbs and a Decision Tree classifier for DMC task. For NER, we utilize Conditional Random Fields (CRFs) in a low-resource setting and report on the reliability and precision for identification of deontic modality. Our experiments reveal that simpler models, like decision trees, out perform larger models in the low-resource setting of DMC obtaining macro-F1 score of 0.83. For the NER task, the CRF models show consistent performance for `obligation' labels with an F1-score of 0.51 but have wavering results for other classes with a max F1-score of 0.26 for `permission', and 0.08 for `prohibition'."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2024-12-16"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Computer and Information Science","Law"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Deontic Modality"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Legal Text"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Natural Language Processing"}}]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Deontic Modality"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Low-Resource Deontic Modality Classification in the EU Legislation"},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"10.34894/HQ8LIH"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://aclanthology.org/2023.nllp-1.15"}},{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Deciphering disagreement in the annotation of EU legislation"},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"10.1007/s10506-024-09423-9"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://link.springer.com/article/10.1007/s10506-024-09423-9"}}]},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["English"]},{"typeName":"productionDate","multiple":false,"typeClass":"primitive","value":"2023-09-01"},{"typeName":"productionPlace","multiple":true,"typeClass":"primitive","value":["Maastricht"]},{"typeName":"contributor","multiple":true,"typeClass":"compound","value":[{"contributorType":{"typeName":"contributorType","multiple":false,"typeClass":"controlledVocabulary","value":"Researcher"},"contributorName":{"typeName":"contributorName","multiple":false,"typeClass":"primitive","value":"Dijck, Gijs van"}}]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Chakravarthy, Shashank"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2024-10-01"},{"typeName":"kindOfData","multiple":true,"typeClass":"primitive","value":["EU Legilsation","Deontic Modality"]},{"typeName":"software","multiple":true,"typeClass":"compound","value":[{"softwareName":{"typeName":"softwareName","multiple":false,"typeClass":"primitive","value":"Lawnotation"},"softwareVersion":{"typeName":"softwareVersion","multiple":false,"typeClass":"primitive","value":"1.0.0"}}]}]},"dansDataVaultMetadata":{"displayName":"Data Vault Metadata","name":"dansDataVaultMetadata","fields":[{"typeName":"dansDataversePid","multiple":false,"typeClass":"primitive","value":"doi:10.34894/D9AKUS"},{"typeName":"dansDataversePidVersion","multiple":false,"typeClass":"primitive","value":"1.0"},{"typeName":"dansBagId","multiple":false,"typeClass":"primitive","value":"urn:uuid:89126ee4-cad2-4f81-883e-ba2b124db449"},{"typeName":"dansNbn","multiple":false,"typeClass":"primitive","value":"urn:nbn:nl:ui:13-b0fb0b4d-8339-4387-a0e9-b6d04cdc8c0b"}]}},"files":[{"description":"For performing NER with CRF","label":"CRF_For_deontic_modality.ipynb","restricted":false,"version":1,"datasetVersionId":29740,"dataFile":{"id":463174,"persistentId":"","filename":"CRF_For_deontic_modality.ipynb","contentType":"application/x-ipynb+json","friendlyType":"Jupyter Notebook","filesize":220670,"description":"For performing NER with CRF","storageIdentifier":"surf://store:193cfd6f561-a92931e0fac8","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"b5beea21dfd6847869dcb22124ac688c8e6a1332"},"tabularData":false,"creationDate":"2024-12-16","publicationDate":"2024-12-17","lastUpdateTime":"2024-12-17T14:04:00Z","fileAccessRequest":true}},{"description":"For testing supervised learning using Decision trees","label":"Decision_tree_classifier_deontic_modality.ipynb","restricted":false,"version":1,"datasetVersionId":29740,"dataFile":{"id":463170,"persistentId":"","filename":"Decision_tree_classifier_deontic_modality.ipynb","contentType":"application/x-ipynb+json","friendlyType":"Jupyter Notebook","filesize":343282,"description":"For testing supervised learning using Decision trees","storageIdentifier":"surf://store:193cfa34645-df61a98f0ad9","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"53c18f2478ecd0900ed72c0dee9341f126f8a692"},"tabularData":false,"creationDate":"2024-12-16","publicationDate":"2024-12-17","lastUpdateTime":"2024-12-17T14:04:00Z","fileAccessRequest":true}},{"description":"File for NER task","label":"deontic.csv","restricted":false,"version":1,"datasetVersionId":29740,"dataFile":{"id":463175,"persistentId":"","filename":"deontic.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":688377,"description":"File for NER task","storageIdentifier":"surf://store:193cfd7a12c-7d8e2feff38a","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"8ddeba05f3c89f97919b2354828e7f777454ab17"},"tabularData":false,"creationDate":"2024-12-16","publicationDate":"2024-12-17","lastUpdateTime":"2024-12-17T14:04:00Z","fileAccessRequest":true}},{"description":"Contains obligations, permissions and prohibitions","label":"df_a1.csv","restricted":false,"version":1,"datasetVersionId":29740,"dataFile":{"id":463169,"persistentId":"","filename":"df_a1.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":54271,"description":"Contains obligations, permissions and prohibitions","storageIdentifier":"surf://store:193cfa35acd-7b841bc8474e","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"5367024df9092d149670244f428b87f070d8fcab"},"tabularData":false,"creationDate":"2024-12-16","publicationDate":"2024-12-17","lastUpdateTime":"2024-12-17T14:04:00Z","fileAccessRequest":true}},{"description":"Using rules and keywords","label":"Rule_based_classifier.ipynb","restricted":false,"version":1,"datasetVersionId":29740,"dataFile":{"id":463168,"persistentId":"","filename":"Rule_based_classifier.ipynb","contentType":"application/x-ipynb+json","friendlyType":"Jupyter Notebook","filesize":220604,"description":"Using rules and keywords","storageIdentifier":"surf://store:193cfa85b78-7ae070c8426a","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"4cc47c81cc8339abbb84b186eb47006e8a195e5d"},"tabularData":false,"creationDate":"2024-12-16","publicationDate":"2024-12-17","lastUpdateTime":"2024-12-17T14:04:00Z","fileAccessRequest":true}}]}}}