{"id":"https://openalex.org/W4284964242","doi":"https://doi.org/10.1142/s1793351x2240013x","title":"To Extend or Not to Extend? Enriching a Corpus with Complementary and Related Documents","display_name":"To Extend or Not to Extend? Enriching a Corpus with Complementary and Related Documents","publication_year":2022,"publication_date":"2022-07-09","ids":{"openalex":"https://openalex.org/W4284964242","doi":"https://doi.org/10.1142/s1793351x2240013x"},"language":"en","primary_location":{"id":"doi:10.1142/s1793351x2240013x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x2240013x","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-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/A5041489447","display_name":"Magnus Bender","orcid":"https://orcid.org/0000-0002-1854-225X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Magnus Bender","raw_affiliation_strings":["Institute of Information Systems, University of L\u00fcbeck, Ratzeburger Allee 160, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Systems, University of L\u00fcbeck, Ratzeburger Allee 160, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029232717","display_name":"Felix Kuhr","orcid":null},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Kuhr","raw_affiliation_strings":["Institute of Information Systems, University of L\u00fcbeck, Ratzeburger Allee 160, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Systems, University of L\u00fcbeck, Ratzeburger Allee 160, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067298045","display_name":"Tanya Braun","orcid":"https://orcid.org/0000-0003-0282-4284"},"institutions":[{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tanya Braun","raw_affiliation_strings":["Computer Science Department University of M\u00fcnster, Einsteinstr. 62, M\u00fcnster, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department University of M\u00fcnster, Einsteinstr. 62, M\u00fcnster, Germany","institution_ids":["https://openalex.org/I22465464"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041489447"],"corresponding_institution_ids":["https://openalex.org/I9341345"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59871547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"16","issue":"04","first_page":"521","last_page":"545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9962000250816345,"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":0.8687031865119934},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.7972162961959839},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7339275479316711},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7260245680809021},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5275335311889648},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5124238133430481},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4996225833892822},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.4943196773529053},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.43329542875289917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41592898964881897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8687031865119934},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.7972162961959839},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7339275479316711},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7260245680809021},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5275335311889648},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5124238133430481},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4996225833892822},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4943196773529053},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.43329542875289917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41592898964881897},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1793351x2240013x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x2240013x","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1552847225","https://openalex.org/W1880344393","https://openalex.org/W2022166150","https://openalex.org/W2049633694","https://openalex.org/W2052390074","https://openalex.org/W2081580037","https://openalex.org/W2086699924","https://openalex.org/W2096266510","https://openalex.org/W2105594594","https://openalex.org/W2142384583","https://openalex.org/W2144211451","https://openalex.org/W2159428510","https://openalex.org/W2251913848","https://openalex.org/W2511642943","https://openalex.org/W2739450958","https://openalex.org/W2963296777","https://openalex.org/W2971443991","https://openalex.org/W2990968482","https://openalex.org/W3091254123","https://openalex.org/W4220713953"],"related_works":["https://openalex.org/W3003553552","https://openalex.org/W2357241418","https://openalex.org/W1987753576","https://openalex.org/W2081647779","https://openalex.org/W2974225181","https://openalex.org/W4288108740","https://openalex.org/W2153717697","https://openalex.org/W4284964242","https://openalex.org/W4220713953","https://openalex.org/W2351265032"],"abstract_inverted_index":{"An":[0],"agent":[1,36],"in":[2,89,115],"pursuit":[3],"of":[4,12,22,61,73,81,92,103],"a":[5,10,26,78,98,107,120],"task":[6,21],"may":[7,49],"work":[8],"with":[9,14],"corpus":[11],"documents":[13,114],"linked":[15],"subjective":[16,86],"content":[17,87],"descriptions.":[18],"Performing":[19],"the":[20,62,84,90,101,104,124],"document":[23],"retrieval":[24],"for":[25,55,109,127],"user":[27],"or":[28,58],"aiming":[29],"to":[30,43],"extend":[31],"its":[32],"own":[33],"corpus,":[34],"an":[35],"so":[37],"far":[38],"relies":[39],"on":[40],"similarity":[41,48],"measures":[42],"identify":[44],"related":[45,113,130],"documents.":[46,131],"However,":[47],"not":[50],"be":[51],"appropriate":[52],"if":[53],"looking":[54],"new":[56],"information":[57],"different":[59],"aspects":[60],"same":[63],"content.":[64],"Therefore,":[65],"this":[66],"paper":[67],"combines":[68],"complementarity-":[69],"and":[70,112,118,129],"similarity-based":[71],"identification":[72],"documents,":[74],"specifically,":[75],"contributing":[76],"(i)":[77],"formal":[79],"definition":[80],"complementarity":[82],"using":[83],"available":[85],"descriptions":[88],"form":[91],"relational":[93],"tuples":[94],"as":[95,97],"well":[96],"taxonomy":[99],"interrelating":[100],"concepts":[102],"tuples,":[105],"(ii)":[106],"technique":[108],"classifying":[110],"complementary":[111,128],"one":[116],"go,":[117],"(iii)":[119],"case":[121],"study":[122],"assessing":[123],"classification":[125],"performance":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
