{"id":"https://openalex.org/W3012827952","doi":"https://doi.org/10.1145/3383583.3398525","title":"Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles","display_name":"Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3012827952","doi":"https://doi.org/10.1145/3383583.3398525","mag":"3012827952"},"language":"en","primary_location":{"id":"doi:10.1145/3383583.3398525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398525","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/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.09881","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051325625","display_name":"Malte Ostendorff","orcid":"https://orcid.org/0000-0003-2077-9907"},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Malte Ostendorff","raw_affiliation_strings":["DFKI GmbH & University of Konstanz, Berlin, Germany","DFKI GmbH & University of Konstanz, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH & University of Konstanz, Berlin, Germany","institution_ids":["https://openalex.org/I189712700"]},{"raw_affiliation_string":"DFKI GmbH & University of Konstanz, Berlin, Germany","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081763922","display_name":"Terry Ruas","orcid":"https://orcid.org/0000-0002-9440-780X"},"institutions":[{"id":"https://openalex.org/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Terry Ruas","raw_affiliation_strings":["University of Wuppertal, Wuppertal, Germany"],"affiliations":[{"raw_affiliation_string":"University of Wuppertal, Wuppertal, Germany","institution_ids":["https://openalex.org/I167360494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038664667","display_name":"Moritz Schubotz","orcid":"https://orcid.org/0000-0001-7141-4997"},"institutions":[{"id":"https://openalex.org/I158675288","display_name":"FIZ Karlsruhe \u2013 Leibniz Institute for Information Infrastructure","ror":"https://ror.org/0387prb75","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I158675288","https://openalex.org/I315704651"]},{"id":"https://openalex.org/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moritz Schubotz","raw_affiliation_strings":["University of Wuppertal & FIZ Karlsruhe, Karlsruhe, Germany","University of Wuppertal & FIZ Karlsruhe, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"University of Wuppertal & FIZ Karlsruhe, Karlsruhe, Germany","institution_ids":["https://openalex.org/I167360494"]},{"raw_affiliation_string":"University of Wuppertal & FIZ Karlsruhe, Karlsruhe, Germany","institution_ids":["https://openalex.org/I158675288","https://openalex.org/I167360494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104366289","display_name":"Georg Rehm","orcid":"https://orcid.org/0000-0002-7800-1893"},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Rehm","raw_affiliation_strings":["DFKI GmbH, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH, Berlin, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058837356","display_name":"B\u00e9la Gipp","orcid":"https://orcid.org/0000-0001-6522-3019"},"institutions":[{"id":"https://openalex.org/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]},{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bela Gipp","raw_affiliation_strings":["University of Konstanz & University of Wuppertal, Wuppertal, Germany","University of Konstanz & University of Wuppertal, Wuppertal, Germany"],"affiliations":[{"raw_affiliation_string":"University of Konstanz & University of Wuppertal, Wuppertal, Germany","institution_ids":["https://openalex.org/I167360494","https://openalex.org/I189712700"]},{"raw_affiliation_string":"University of Konstanz & University of Wuppertal, Wuppertal, Germany","institution_ids":["https://openalex.org/I167360494","https://openalex.org/I189712700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051325625"],"corresponding_institution_ids":["https://openalex.org/I189712700"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02879088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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":0.9987000226974487,"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":0.8502155542373657},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7376133799552917},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5322356820106506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5263494253158569},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.524226725101471},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47696220874786377},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.4428877830505371},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.417567640542984},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3989322781562805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3350042402744293},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2795785665512085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8502155542373657},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7376133799552917},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5322356820106506},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5263494253158569},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.524226725101471},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47696220874786377},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.4428877830505371},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.417567640542984},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3989322781562805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3350042402744293},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2795785665512085},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3383583.3398525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398525","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/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.09881","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.09881","pdf_url":"https://arxiv.org/pdf/2003.09881","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2003.09881","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.09881","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3012827952","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.09881","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.09881","pdf_url":"https://arxiv.org/pdf/2003.09881","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3012827952.pdf","grobid_xml":"https://content.openalex.org/works/W3012827952.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W168564468","https://openalex.org/W941230081","https://openalex.org/W1015675232","https://openalex.org/W1566289585","https://openalex.org/W1994925058","https://openalex.org/W2080133951","https://openalex.org/W2100059775","https://openalex.org/W2101234009","https://openalex.org/W2123437718","https://openalex.org/W2131744502","https://openalex.org/W2153064622","https://openalex.org/W2171590421","https://openalex.org/W2250539671","https://openalex.org/W2419427031","https://openalex.org/W2518202280","https://openalex.org/W2753177113","https://openalex.org/W2898725686","https://openalex.org/W2900979343","https://openalex.org/W2907230994","https://openalex.org/W2913433659","https://openalex.org/W2939507640","https://openalex.org/W2950577311","https://openalex.org/W2952179106","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963918774","https://openalex.org/W2964110616","https://openalex.org/W2965641629","https://openalex.org/W2970597249","https://openalex.org/W2970641574","https://openalex.org/W2970771982","https://openalex.org/W2970930899","https://openalex.org/W2972324944","https://openalex.org/W2980282514","https://openalex.org/W2983050946","https://openalex.org/W2990070951","https://openalex.org/W2997591727","https://openalex.org/W3004408834","https://openalex.org/W3105994699","https://openalex.org/W4211059094"],"related_works":["https://openalex.org/W3046467166","https://openalex.org/W3093062943","https://openalex.org/W2465754684","https://openalex.org/W2287180041","https://openalex.org/W3194958284","https://openalex.org/W1996476189","https://openalex.org/W2136275147","https://openalex.org/W2911997761","https://openalex.org/W897062481","https://openalex.org/W2950220747","https://openalex.org/W9516802","https://openalex.org/W1570554959","https://openalex.org/W2135330499","https://openalex.org/W3035169528","https://openalex.org/W2062901386","https://openalex.org/W2907632654","https://openalex.org/W2252071100","https://openalex.org/W2436312382","https://openalex.org/W1664304127","https://openalex.org/W3038095446"],"abstract_inverted_index":{"Many":[0],"digital":[1],"libraries":[2],"recommend":[3],"literature":[4],"to":[5,22,133,138],"their":[6,16],"users":[7],"considering":[8],"the":[9,26,38,42,55,88,110,120,156,164,177],"similarity":[10],"between":[11,44,58,148],"a":[12,48,62,84,96,151,159],"query":[13],"document":[14,50,112],"and":[15,72,105,154],"repository.":[17],"However,":[18],"they":[19],"often":[20],"fail":[21],"distinguish":[23],"what":[24],"is":[25,150],"relationship":[27,43],"that":[28,108,144,185,190],"makes":[29],"two":[30,45],"documents":[31,46,149,180,189],"alike.":[32],"In":[33],"this":[34,170],"paper,":[35],"we":[36,60,130],"model":[37],"problem":[39],"of":[40,64,100,127,158,179],"finding":[41],"as":[47,67,119,173],"pairwise":[49],"classification":[51],"task.":[52],"To":[53],"find":[54,188],"semantic":[56,111,146],"relation":[57],"documents,":[59],"apply":[61],"series":[63],"techniques,":[65],"such":[66,184],"GloVe,":[68],"Paragraph":[69],"Vectors,":[70],"BERT,":[71],"XLNet":[73],"under":[74],"different":[75],"configurations":[76],"(e.g.,":[77],"sequence":[78],"length,":[79],"vector":[80],"concatenation":[81],"scheme),":[82],"including":[83],"Siamese":[85],"architecture":[86],"for":[87],"Transformer-based":[89],"systems.":[90],"We":[91],"perform":[92],"our":[93],"experiments":[94],"on":[95,163],"newly":[97],"proposed":[98],"dataset":[99],"32,168":[101],"Wikipedia":[102],"article":[103],"pairs":[104],"Wikidata":[106],"properties":[107],"define":[109],"relations.":[113],"Our":[114,141],"results":[115],"show":[116],"vanilla":[117],"BERT":[118],"best":[121],"performing":[122],"system":[123,161],"with":[124],"an":[125],"F1-score":[126],"0.93,":[128],"which":[129],"manually":[131],"examine":[132],"better":[134],"understand":[135],"its":[136],"applicability":[137],"other":[139],"domains.":[140],"findings":[142],"suggest":[143],"classifying":[145],"relations":[147],"solvable":[152],"task":[153],"motivates":[155],"development":[157],"recommender":[160],"based":[162],"evaluated":[165],"techniques.":[166],"The":[167],"discussions":[168],"in":[169,176,193,198],"paper":[171],"serve":[172],"first":[174],"steps":[175],"exploration":[178],"through":[181],"SPARQL-like":[182],"queries":[183],"one":[186,194],"could":[187],"are":[191],"similar":[192],"aspect":[195],"but":[196],"dissimilar":[197],"another.":[199]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}