{"data":{"id":"10.6084/m9.figshare.6388346","type":"dois","attributes":{"doi":"10.6084/m9.figshare.6388346","prefix":"10.6084","suffix":"m9.figshare.6388346","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"SOUZA, Jackson Wilke da Cruz","givenName":"Jackson Wilke da Cruz","familyName":"SOUZA","affiliation":[],"nameIdentifiers":[]},{"name":"FELIPPO, Ariani Di","givenName":"Ariani Di","familyName":"FELIPPO","affiliation":[],"nameIdentifiers":[]}],"titles":[{"title":"CHARACTERIZATION OF TEMPORAL COMPLEMENTARITY: FUNDAMENTALS FOR MULTI-DOCUMENT SUMMARIZATION"}],"publisher":"SciELO journals","container":{},"publicationYear":2018,"subjects":[{"subject":"Linguistics"},{"subject":"FOS: Languages and literature","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"}],"contributors":[],"dates":[{"date":"2018-05-30","dateType":"Created"},{"date":"2022-06-08","dateType":"Updated"},{"date":"2018","dateType":"Issued"}],"language":null,"types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.1590/1981-5794-1804-6","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["77312 Bytes"],"formats":[],"version":null,"rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"ABSTRACT Complementarity is a usual multi-document phenomenon that commonly occurs among news texts about the same event. From a set of sentence pairs (in Portuguese) manually annotated with CST (Cross-Document Structure Theory) relations (Historical background and Follow-up) that make explicit the temporal complementary among the sentences, we identified a potential set of linguistic attributes of such complementary. Using Machine Learning algorithms, we evaluate the capacity of the attributes to discriminate between Historical background and Follow-up. JRip learned a small set of rules with high accuracy. Based on a set of 5 rules, the classifier discriminates the CST relations with 80% of accuracy. According to the rules, the occurrence of temporal expression in sentence 2 is the most discriminative feature in the task. As a contribution, the JRip classifier can improve the performance of the CST-discourse parsers for Brazilian Portuguese","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://scielo.figshare.com/articles/dataset/CHARACTERIZATION_OF_TEMPORAL_COMPLEMENTARITY_FUNDAMENTALS_FOR_MULTI-DOCUMENT_SUMMARIZATION/6388346","contentUrl":null,"metadataVersion":3,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":1,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2018-05-30T02:48:04.000Z","registered":"2018-05-30T02:48:04.000Z","published":"2018","updated":"2022-06-08T23:25:11.000Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}},"provider":{"data":{"id":"otjm","type":"providers"}},"media":{"data":{"id":"10.6084/m9.figshare.6388346","type":"media"}},"references":{"data":[{"id":"10.1590/1981-5794-1804-6","type":"dois"}]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}