{"id":"https://openalex.org/W4281650060","doi":"https://doi.org/10.1145/3529372.3530912","title":"Specialized document embeddings for aspect-based similarity of research papers","display_name":"Specialized document embeddings for aspect-based similarity of research papers","publication_year":2022,"publication_date":"2022-06-06","ids":{"openalex":"https://openalex.org/W4281650060","doi":"https://doi.org/10.1145/3529372.3530912"},"language":"en","primary_location":{"id":"doi:10.1145/3529372.3530912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529372.3530912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/136255","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/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":"Malte Ostendorff","raw_affiliation_strings":["DFKI GmbH, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI GmbH, Berlin, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044184308","display_name":"Till Blume","orcid":"https://orcid.org/0000-0001-6970-9489"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Till Blume","raw_affiliation_strings":["Ernst & Young GmbH WPG - R&D, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ernst & Young GmbH WPG - R&D, Berlin, Germany","institution_ids":[]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wuppertal, Wuppertal, Germany","institution_ids":["https://openalex.org/I167360494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058837356","display_name":"B\u00e9la Gipp","orcid":"https://orcid.org/0000-0001-6522-3019"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bela Gipp","raw_affiliation_strings":["University of G\u00f6ttingen, G\u00f6ttingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI GmbH, Berlin, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3617,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90417576,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9968000054359436,"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":0.7140535712242126},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7050132751464844},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6666494011878967},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6071369051933289},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5642039775848389},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5340479612350464},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5209978222846985},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4637018144130707},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.44994866847991943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4277106523513794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3520527482032776},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.18581831455230713},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12959802150726318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7140535712242126},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7050132751464844},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6666494011878967},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6071369051933289},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5642039775848389},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5340479612350464},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5209978222846985},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4637018144130707},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.44994866847991943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4277106523513794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3520527482032776},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.18581831455230713},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12959802150726318},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3529372.3530912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529372.3530912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/136255","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/136255","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:publications.goettingen-research-online.de:2/136255","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/136255","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4140173886","display_name":null,"funder_award_id":"03COV03E","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G8954702977","display_name":null,"funder_award_id":"03WKDA1A","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1010415138","https://openalex.org/W1488279396","https://openalex.org/W1503259811","https://openalex.org/W1888005072","https://openalex.org/W1973610950","https://openalex.org/W2001259128","https://openalex.org/W2049870103","https://openalex.org/W2122111042","https://openalex.org/W2126793736","https://openalex.org/W2160660844","https://openalex.org/W2161676175","https://openalex.org/W2165664073","https://openalex.org/W2171590421","https://openalex.org/W2171700594","https://openalex.org/W2251648804","https://openalex.org/W2490986620","https://openalex.org/W2493916176","https://openalex.org/W2561675875","https://openalex.org/W2586601519","https://openalex.org/W2618160968","https://openalex.org/W2620558438","https://openalex.org/W2747329762","https://openalex.org/W2757662681","https://openalex.org/W2767187055","https://openalex.org/W2798962680","https://openalex.org/W2807563359","https://openalex.org/W2882319491","https://openalex.org/W2883627503","https://openalex.org/W2895547478","https://openalex.org/W2898725686","https://openalex.org/W2899754878","https://openalex.org/W2900979343","https://openalex.org/W2941411956","https://openalex.org/W2962739339","https://openalex.org/W2963081391","https://openalex.org/W2963850840","https://openalex.org/W2964169023","https://openalex.org/W2970641574","https://openalex.org/W2970771982","https://openalex.org/W2998184481","https://openalex.org/W3023556039","https://openalex.org/W3034999214","https://openalex.org/W3035391452","https://openalex.org/W3046467166","https://openalex.org/W3103940211","https://openalex.org/W3105949609","https://openalex.org/W3115413024","https://openalex.org/W3163014027","https://openalex.org/W3191638286","https://openalex.org/W3201382782","https://openalex.org/W3212007825","https://openalex.org/W3213844504","https://openalex.org/W4213009331","https://openalex.org/W4213122582","https://openalex.org/W4240432412","https://openalex.org/W4281492236","https://openalex.org/W4287695425","https://openalex.org/W4365799947"],"related_works":["https://openalex.org/W1968265719","https://openalex.org/W2538371562","https://openalex.org/W3046994506","https://openalex.org/W2045631426","https://openalex.org/W1751894661","https://openalex.org/W4238415164","https://openalex.org/W2137763598","https://openalex.org/W932910286","https://openalex.org/W2545327431","https://openalex.org/W2142127980"],"abstract_inverted_index":{"Document":[0],"embeddings":[1,162,222,241],"and":[2,113,136,141,153,163,183,200,227,262],"similarity":[3,21,33,47,82,87],"measures":[4,48],"underpin":[5],"content-based":[6],"recommender":[7],"systems,":[8],"whereby":[9],"a":[10,16,84,95,99,164],"document":[11,32,53,58,64,96,111,157,161,177,189,221,240],"is":[12],"commonly":[13],"represented":[14],"as":[15,83,98,104,148],"single":[17,24,100],"generic":[18,101,156,176,220],"embedding.":[19],"However,":[20],"computed":[22],"on":[23,31],"vector":[25,86],"representations":[26],"provides":[27],"only":[28],"one":[29],"perspective":[30],"that":[34],"ignores":[35],"which":[36],"aspects":[37],"make":[38],"two":[39],"documents":[40],"alike.":[41],"To":[42,185],"address":[43],"this":[44,77],"limitation,":[45],"aspect-based":[46,81,239],"have":[49],"been":[50],"developed":[51],"using":[52],"segmentation":[54,61,112],"or":[55],"pairwise":[56,67,165],"multi-class":[57],"classification.":[59],"While":[60],"harms":[62],"the":[63,66,117,126,138,144,169,187,209,219,224,229],"coherence,":[65],"classification":[68,166],"approach":[69,109,237],"scales":[70,114],"poorly":[71],"to":[72],"large":[73],"scale":[74],"corpora.":[75],"In":[76,120,203],"paper,":[78],"we":[79,124,179,191],"treat":[80],"classical":[85],"problem":[88],"in":[89,168],"aspect-specific":[90],"embedding":[91,102],"spaces.":[92],"We":[93,151],"represent":[94],"not":[97],"but":[103],"multiple":[105],"specialized":[106,160,188],"embeddings.":[107],"Our":[108,236],"avoids":[110],"linearly":[115],"w.r.t.":[116],"corpus":[118,130],"size.":[119],"an":[121,215],"empirical":[122],"study,":[123],"use":[125],"Papers":[127],"with":[128],"Code":[129],"containing":[131],"157,":[132],"606":[133],"research":[134,146,172,234],"papers":[135,147],"consider":[137,180],"task,":[139],"method,":[140],"dataset":[142,225],"of":[143,171,218,232,238],"respective":[145],"their":[149],"aspects.":[150],"compare":[152,192],"analyze":[154],"three":[155,193],"embeddings,":[158,178,190],"six":[159],"baseline":[167],"context":[170],"paper":[173],"recommendations.":[174,264],"As":[175],"FastText,":[181],"SciBERT,":[182],"SPECTER.":[184],"compute":[186],"alternative":[194],"methods":[195],"inspired":[196],"by":[197,249],"retrofitting,":[198],"fine-tuning,":[199],"Siamese":[201,206],"networks.":[202],"our":[204],"experiments,":[205],"SciBERT":[207],"achieved":[208],"highest":[210],"scores.":[211],"Additional":[212],"analyses":[213],"indicate":[214],"implicit":[216,247],"bias":[217],"towards":[223],"aspect":[226,231],"against":[228],"method":[230],"each":[233],"paper.":[235],"mitigates":[242],"potential":[243],"risks":[244],"arising":[245],"from":[246],"biases":[248],"making":[250],"them":[251],"explicit.":[252],"This":[253],"can,":[254],"for":[255,259],"example,":[256],"be":[257],"used":[258],"more":[260],"diverse":[261],"explainable":[263]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}