{"dcterms:modified":"2024-01-18","dcterms:creator":"heiDATA","@type":"ore:ResourceMap","schema:additionalType":"Dataverse OREMap Format v1.0.0","dvcore:generatedBy":{"@type":"schema:SoftwareApplication","schema:name":"Dataverse","schema:version":"6.1 build 1590-f5d1299","schema:url":"https://github.com/iqss/dataverse"},"@id":"https://heidata.uni-heidelberg.de/api/datasets/export?exporter=OAI_ORE&persistentId=https://doi.org/10.11588/data/QKF4LT","ore:describes":{"publication":{"publicationCitation":"
Ruppenhofer, J., Wiegand, M., Wilm, R., and Markert, K. (2018). Distinguishing affixoid formations from compounds. In Proceedings of the International Conference on Computational Linguistics, pages 3853–3865, August 20-26, 2018, Santa Fe, NM, USA.
","publicationIDType":"url","publicationIDNumber":"https://www.aclweb.org/anthology/C18-1325","publicationURL":"https://www.aclweb.org/anthology/C18-1325"},"citation:dsDescription":{"citation:dsDescriptionValue":"The dataset contains the manual annotations for the COLING 2018 \r\nsubmission \"Distinguishing affixoid formations from compounds\" by Josef \r\nRuppenhofer, Michael Wiegand, Rebecca Wilm and Katja Markert.\r\n\r\n1788 complex words containing one of 7 German suffixoid candidates (e.g. \r\n-hai, -gott) were annotated manually as to whether the complex forms \r\nrepresent regular compounds or affixoid formations. The main experiments \r\nin the paper use automatically extracted features of the complex forms \r\nin trying to correctly make this distinction.\r\n\r\nAdditionally, the words were labeled for five properties related to any \r\nintensifying and evaluative meaning potentially associated with the \r\nwhole word and its components. These manual feature annotations were \r\nused to establish the upper-bound performance of a classifier trained \r\nto distinguish affixoid formations from regular compounds."},"citation:datasetContact":{"citation:datasetContactName":"Ruppenhofer, Josef","citation:datasetContactAffiliation":"Leibniz Institute for the German Language","citation:datasetContactEmail":"ruppenhofer@ids-mannheim.de"},"author":{"citation:authorName":"Ruppenhofer, Josef","citation:authorAffiliation":"Leibniz Institute for the German Language"},"title":"Affixoid Dataset (DE)","subject":["Arts and Humanities","Computer and Information Science"],"dateOfDeposit":"2019-07-31","citation:topicClassification":[{"citation:topicClassValue":"sentiment"},{"citation:topicClassValue":"affixoid classification"}],"citation:keyword":[{"citation:keywordValue":"morphology"},{"citation:keywordValue":"entiment analysis"},{"citation:keywordValue":"compound"},{"citation:keywordValue":"affixoid"},{"citation:keywordValue":"German"}],"citation:productionPlace":"Institute for German Language Mannheim, Heidelberg University","citation:productionDate":"2018","kindOfData":"textual data, CSV text file format","alternativeURL":"https://github.com/josefkr/affixoids","@id":"https://doi.org/10.11588/data/QKF4LT","@type":["ore:Aggregation","schema:Dataset"],"schema:version":"1.0","schema:name":"Affixoid Dataset (DE)","schema:dateModified":"Tue Oct 08 11:27:31 CEST 2019","schema:datePublished":"2019-10-08","schema:creativeWorkStatus":"RELEASED","dvcore:termsOfUse":"Licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
","dvcore:fileTermsOfAccess":{"dvcore:fileRequestAccess":false},"schema:includedInDataCatalog":"heiDATA","schema:isPartOf":{"schema:name":"Empirical Linguistics and Computational Language Modeling (LiMo)","@id":"https://heidata.uni-heidelberg.de/dataverse/lwc-limo","schema:description":"Data publications of the Leibniz ScienceCampus “Empirical Linguistics and Computational Language Modeling”
\r\nThe Leibniz ScienceCampus “Empirical Linguistics and Computational Language Modeling” (LiMo) is a cooperative research project between the Leibniz Institute for the German Language (Leibniz-Institut für Deutsche Sprache, IDS) in Mannheim and the Department of Computational Linguistics at Heidelberg University (ICL). The general aims of the project are to develop new methods, models, and tools for compiling and analysing automatically large German textual corpora covering different domains, genres and language varieties.
\r\nThe project is supported by funds from the Baden-Württemberg Ministry of Science, Research and the Arts and the Leibniz Association together with funds provided by the Leibniz Institute for the German Language and Heidelberg University.
\r\nFunding Period: 2015 – 2020
\r\n","schema:isPartOf":{"schema:name":"heiDATA","@id":"https://heidata.uni-heidelberg.de/dataverse/root","schema:description":"heiDATA is an institutional repository for Open Research Data from Heidelberg University. It is managed by the Competence Centre for Research Data, a joint institution of the University Library and the Computing Centre. If you are interested in publishing your data here, please have a look at our user guide and get in touch with us. Detailed information on heiDATA can be found in our service description."}},"ore:aggregates":[{"schema:name":"dataset_annotations.csv","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":440,"dvcore:categories":["Data"],"@id":"doi:10.11588/data/QKF4LT/4CPCOZ","schema:sameAs":"https://heidata.uni-heidelberg.de/api/access/datafile/:persistentId?persistentId=doi:10.11588/data/QKF4LT/4CPCOZ&format=original","@type":"ore:AggregatedResource","schema:fileFormat":"text/csv","dvcore:filesize":48812,"dvcore:storageIdentifier":"file://16d00f26bbe-15099bef7f19","dvcore:currentIngestedName":"dataset_annotations.tab","dvcore:UNF":"UNF:6:+MGK9lTPTXx7Rclu1BpPnw==","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"8e2e107227a8ab7d59fb9a48dfa9f475"}},{"schema:name":"README.txt","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":440,"dvcore:categories":["Documentation"],"@id":"doi:10.11588/data/QKF4LT/ARVFSU","schema:sameAs":"https://heidata.uni-heidelberg.de/api/access/datafile/:persistentId?persistentId=doi:10.11588/data/QKF4LT/ARVFSU","@type":"ore:AggregatedResource","schema:fileFormat":"text/plain","dvcore:filesize":758,"dvcore:storageIdentifier":"file://16d00f26d5f-4125b8299cea","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"017f60a9c77782cd97a45c4dd74e117c"}}],"schema:hasPart":["doi:10.11588/data/QKF4LT/4CPCOZ","doi:10.11588/data/QKF4LT/ARVFSU"]},"@context":{"alternativeURL":"https://schema.org/distribution","author":"http://purl.org/dc/terms/creator","citation":"https://dataverse.org/schema/citation/","dateOfDeposit":"http://purl.org/dc/terms/dateSubmitted","dcterms":"http://purl.org/dc/terms/","dvcore":"https://dataverse.org/schema/core#","kindOfData":"http://rdf-vocabulary.ddialliance.org/discovery#kindOfData","ore":"http://www.openarchives.org/ore/terms/","publication":"http://purl.org/dc/terms/isReferencedBy","publicationCitation":"http://purl.org/dc/terms/bibliographicCitation","publicationIDNumber":"http://purl.org/spar/datacite/ResourceIdentifier","publicationIDType":"http://purl.org/spar/datacite/ResourceIdentifierScheme","publicationURL":"https://schema.org/distribution","schema":"http://schema.org/","subject":"http://purl.org/dc/terms/subject","title":"http://purl.org/dc/terms/title"}}