{"id":"https://openalex.org/W2894811299","doi":"https://doi.org/10.1145/3209280.3229098","title":"Semantically Weighted Similarity Analysis for XML-based Content Components","display_name":"Semantically Weighted Similarity Analysis for XML-based Content Components","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2894811299","doi":"https://doi.org/10.1145/3209280.3229098","mag":"2894811299"},"language":"en","primary_location":{"id":"doi:10.1145/3209280.3229098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209280.3229098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065713891","display_name":"Jan Oevermann","orcid":"https://orcid.org/0000-0002-0415-4782"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jan Oevermann","raw_affiliation_strings":["University of Bremen &amp; German Research Center for Artificial Intelligence (DFKI), Bremen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bremen &amp; German Research Center for Artificial Intelligence (DFKI), Bremen, Germany","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I180437899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081578222","display_name":"Christoph L\u00fcth","orcid":"https://orcid.org/0000-0002-1121-398X"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph L\u00fcth","raw_affiliation_strings":["University of Bremen &amp; German Research Center for Artificial Intelligence (DFKI), Bremen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bremen &amp; German Research Center for Artificial Intelligence (DFKI), Bremen, Germany","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I180437899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065713891"],"corresponding_institution_ids":["https://openalex.org/I180437899","https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10863749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9991999864578247,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.8200584650039673},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.7118338346481323},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6980790495872498},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6909251809120178},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6820581555366516},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6766044497489929},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6607254147529602},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5278705954551697},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4936598241329193},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2667894959449768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17768681049346924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0618952214717865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8200584650039673},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7118338346481323},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6980790495872498},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6909251809120178},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6820581555366516},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6766044497489929},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6607254147529602},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5278705954551697},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4936598241329193},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2667894959449768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17768681049346924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0618952214717865},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3209280.3229098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209280.3229098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4116159416","display_name":null,"funder_award_id":"01IW16001","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1566018662","https://openalex.org/W1646006088","https://openalex.org/W1968561693","https://openalex.org/W2097788293","https://openalex.org/W2121184547","https://openalex.org/W2512965824","https://openalex.org/W2782642723"],"related_works":["https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W2353602216","https://openalex.org/W2367078749","https://openalex.org/W2381798600","https://openalex.org/W1910583078","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349"],"abstract_inverted_index":{"Uncontrolled":[0],"variants":[1,41],"and":[2,29,39],"duplicate":[3],"content":[4,10,18],"are":[5],"ongoing":[6],"problems":[7],"in":[8,42],"component":[9],"management;":[11],"they":[12],"decrease":[13],"the":[14,34],"overall":[15],"reuse":[16],"of":[17,37],"components.":[19],"Similarity":[20],"analyses":[21],"can":[22],"help":[23],"to":[24],"clean":[25],"up":[26],"existing":[27],"databases":[28],"identify":[30],"problematic":[31],"texts,":[32],"however,":[33],"large":[35],"amount":[36],"data":[38],"intentional":[40],"technical":[43],"texts":[44],"make":[45],"this":[46],"a":[47],"challenging":[48],"task.":[49]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
