{"id":"https://openalex.org/W3187022580","doi":"https://doi.org/10.1007/s10579-021-09552-6","title":"Labelling the past: data set creation and multi-label classification of Dutch archaeological excavation reports","display_name":"Labelling the past: data set creation and multi-label classification of Dutch archaeological excavation reports","publication_year":2021,"publication_date":"2021-07-28","ids":{"openalex":"https://openalex.org/W3187022580","doi":"https://doi.org/10.1007/s10579-021-09552-6","mag":"3187022580"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-021-09552-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-021-09552-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-021-09552-6.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-021-09552-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067546540","display_name":"Alex Brandsen","orcid":"https://orcid.org/0000-0003-1623-1340"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alex Brandsen","raw_affiliation_strings":["Faculty of Archaeology, Einsteinweg 2, 2333CC, Leiden, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1623-1340","affiliations":[{"raw_affiliation_string":"Faculty of Archaeology, Einsteinweg 2, 2333CC, Leiden, The Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045801712","display_name":"Martin Koole","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Koole","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Niels Bohrweg 1, 2333CA, Leiden, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Niels Bohrweg 1, 2333CA, Leiden, The Netherlands","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5067546540"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5199,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72850166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"56","issue":"2","first_page":"543","last_page":"572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/excavation","display_name":"Excavation","score":0.885102391242981},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6569873690605164},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5708279013633728},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5553010106086731},{"id":"https://openalex.org/keywords/labelling","display_name":"Labelling","score":0.5484545826911926},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.524334728717804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4897427558898926},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47884654998779297},{"id":"https://openalex.org/keywords/grey-literature","display_name":"Grey literature","score":0.4263855218887329},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.23026752471923828},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.06081065535545349}],"concepts":[{"id":"https://openalex.org/C31858485","wikidata":"https://www.wikidata.org/wiki/Q959782","display_name":"Excavation","level":2,"score":0.885102391242981},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6569873690605164},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5708279013633728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5553010106086731},{"id":"https://openalex.org/C2780523633","wikidata":"https://www.wikidata.org/wiki/Q380709","display_name":"Labelling","level":2,"score":0.5484545826911926},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.524334728717804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4897427558898926},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47884654998779297},{"id":"https://openalex.org/C61904560","wikidata":"https://www.wikidata.org/wiki/Q1148359","display_name":"Grey literature","level":3,"score":0.4263855218887329},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.23026752471923828},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.06081065535545349},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s10579-021-09552-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-021-09552-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-021-09552-6.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:ul:oai:scholarlypublications.universiteitleiden.nl:item_3203934","is_oa":true,"landing_page_url":"http://hdl.handle.net/1887/3203934","pdf_url":"http://hdl.handle.net/1887/3203934","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation. Springer Science and Business Media LLC","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_3256309","is_oa":true,"landing_page_url":"https://hdl.handle.net/1887/3256309","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation","raw_type":"Article / Letter to editor"},{"id":"pmh:ul:oai:scholarlypublications.universiteitleiden.nl:item_3256309","is_oa":true,"landing_page_url":"http://hdl.handle.net/1887/3256309","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation. SPRINGER","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.5281/zenodo.3676703","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3676703","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"doi:10.1007/s10579-021-09552-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-021-09552-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-021-09552-6.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187022580.pdf","grobid_xml":"https://content.openalex.org/works/W3187022580.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W46659105","https://openalex.org/W2027868102","https://openalex.org/W2094288026","https://openalex.org/W2099599054","https://openalex.org/W2101156862","https://openalex.org/W2109668015","https://openalex.org/W2137484796","https://openalex.org/W2149684865","https://openalex.org/W2163167319","https://openalex.org/W2183913575","https://openalex.org/W2595644810","https://openalex.org/W2896457183","https://openalex.org/W2921553604","https://openalex.org/W2971296908","https://openalex.org/W2984930866","https://openalex.org/W3005743304","https://openalex.org/W3021503072","https://openalex.org/W3023933756","https://openalex.org/W3031359449","https://openalex.org/W3133881579","https://openalex.org/W3208649660","https://openalex.org/W3212421086","https://openalex.org/W4246035281","https://openalex.org/W4287643567","https://openalex.org/W6735079933","https://openalex.org/W6931012696"],"related_works":["https://openalex.org/W1976633635","https://openalex.org/W2396436470","https://openalex.org/W1970064489","https://openalex.org/W4241622628","https://openalex.org/W2070829827","https://openalex.org/W2078502149","https://openalex.org/W1991894391","https://openalex.org/W2380886523","https://openalex.org/W2228761597","https://openalex.org/W2017465692"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"extraction":[2],"of":[3,26,47,71,78,88],"information":[4,23],"from":[5],"Dutch":[6],"archaeological":[7,48],"grey":[8],"literature":[9],"has":[10],"recently":[11],"been":[12],"investigated":[13],"by":[14,24],"the":[15,45,79,84],"AGNES":[16,18],"project.":[17],"aims":[19],"to":[20,31,34,64,82,103],"disclose":[21],"relevant":[22],"means":[25],"a":[27,59,69],"web":[28],"search":[29,35],"engine,":[30],"enable":[32],"researchers":[33],"through":[36],"excavation":[37,49],"reports.":[38],"In":[39],"this":[40,65],"paper,":[41],"we":[42],"focus":[43],"on":[44],"multi-labelling":[46],"reports":[50],"with":[51],"time":[52],"periods":[53],"and":[54,57,75,91],"site":[55],"types,":[56],"provide":[58],"manually":[60],"labelled":[61],"reference":[62],"set":[63,81],"end.":[66],"We":[67,93],"propose":[68],"series":[70],"approaches,":[72],"pre-processing":[73],"methods,":[74],"various":[76],"modifications":[77],"training":[80],"address":[83],"often":[85],"low":[86],"quality":[87],"both":[89],"texts":[90],"labels.":[92],"find":[94],"that":[95],"despite":[96],"those":[97],"issues,":[98],"our":[99],"proposed":[100],"methods":[101],"lead":[102],"promising":[104],"results.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
