{"id":"https://openalex.org/W2974442661","doi":"https://doi.org/10.1145/3342558.3345424","title":"Combining Word Embeddings with Taxonomy Information for Multi-Label Document Classification","display_name":"Combining Word Embeddings with Taxonomy Information for Multi-Label Document Classification","publication_year":2019,"publication_date":"2019-09-19","ids":{"openalex":"https://openalex.org/W2974442661","doi":"https://doi.org/10.1145/3342558.3345424","mag":"2974442661"},"language":"en","primary_location":{"id":"doi:10.1145/3342558.3345424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342558.3345424","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 2019","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/A5005848538","display_name":"Stefan Hirschmeier","orcid":"https://orcid.org/0000-0002-3754-5261"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Stefan Hirschmeier","raw_affiliation_strings":["University of Cologne, Cologne Germany"],"affiliations":[{"raw_affiliation_string":"University of Cologne, Cologne Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010170517","display_name":"Detlef Schoder","orcid":null},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Detlef Schoder","raw_affiliation_strings":["University of Cologne, Cologne Germany"],"affiliations":[{"raw_affiliation_string":"University of Cologne, Cologne Germany","institution_ids":["https://openalex.org/I180923762"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005848538"],"corresponding_institution_ids":["https://openalex.org/I180923762"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65950635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T11550","display_name":"Text and Document Classification Technologies","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9993000030517578,"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":0.9943000078201294,"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":0.7995597124099731},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.7533872723579407},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6311854124069214},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5993887186050415},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5987998247146606},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5962602496147156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5700492262840271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5187068581581116},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.48905882239341736},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4492817223072052},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42390769720077515},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10004213452339172},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08954980969429016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995597124099731},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.7533872723579407},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6311854124069214},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5993887186050415},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5987998247146606},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5962602496147156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5700492262840271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5187068581581116},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.48905882239341736},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4492817223072052},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42390769720077515},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10004213452339172},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08954980969429016},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3342558.3345424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342558.3345424","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 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W42251416","https://openalex.org/W1423339008","https://openalex.org/W1567491469","https://openalex.org/W1614298861","https://openalex.org/W1832693441","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W1984052055","https://openalex.org/W2100693535","https://openalex.org/W2118772635","https://openalex.org/W2131744502","https://openalex.org/W2146769536","https://openalex.org/W2147152072","https://openalex.org/W2153579005","https://openalex.org/W2585540825","https://openalex.org/W2616922365","https://openalex.org/W2618381521","https://openalex.org/W2737829698","https://openalex.org/W2775160269","https://openalex.org/W2950577311","https://openalex.org/W2963274420","https://openalex.org/W2964046515","https://openalex.org/W4205184193","https://openalex.org/W6636440780","https://openalex.org/W6719819555","https://openalex.org/W6738194712"],"related_works":["https://openalex.org/W4286432911","https://openalex.org/W2901841427","https://openalex.org/W2798669739","https://openalex.org/W2953242939","https://openalex.org/W2997627311","https://openalex.org/W2612746495","https://openalex.org/W4292355215","https://openalex.org/W2289741972","https://openalex.org/W2580878117","https://openalex.org/W4296501933"],"abstract_inverted_index":{"In":[0],"business":[1],"contexts,":[2],"documents":[3,45],"often":[4],"need":[5],"to":[6,29,82,108,124],"be":[7,30],"classified":[8],"using":[9],"company-specific":[10],"taxonomies.":[11],"Text-classification":[12],"approaches":[13],"based":[14,135],"on":[15,136],"word":[16,137],"embeddings":[17,138],"have":[18,60],"become":[19],"increasingly":[20],"popular":[21],"as":[22],"they":[23,80],"enable":[24],"words,":[25],"documents,":[26],"and":[27,43,46],"tags":[28,47,115],"represented":[31],"in":[32,49,84,100,113],"a":[33,117],"semantically":[34],"robust":[35],"way":[36],"(as":[37],"distributed":[38,56],"representations":[39,57],"of":[40,58,74,96,105,116,128],"their":[41,61],"contexts)":[42],"make":[44],"processable":[48],"an":[50,122],"algebraic":[51],"vector":[52],"space.":[53],"However,":[54],"these":[55],"contexts":[59,73],"shortcomings":[62],"when":[63],"used":[64],"for":[65,131],"multi-label":[66,132],"classification":[67,133],"tasks:":[68],"the":[69,72,77,97,126],"more":[70,78],"similar":[71],"two":[75],"tags,":[76],"difficult":[79],"are":[81],"separate":[83],"classification.":[85],"Intensified":[86],"by":[87,139],"poor":[88,91],"training":[89],"data,":[90],"training,":[92],"or":[93],"inherent":[94],"limitations":[95],"word-embedding":[98],"approach,":[99],"practice,":[101],"we":[102],"find":[103],"areas":[104,130],"indistinguishability,":[106],"leading":[107],"false":[109],"positive":[110],"predictions":[111],"(typically":[112],"leaf":[114],"taxonomy":[118,141],"tree).":[119],"We":[120],"contribute":[121],"approach":[123],"tackle":[125],"problem":[127],"indistinguishable":[129],"tasks":[134],"including":[140],"information":[142],"during":[143],"prediction.":[144]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}