{"id":"https://openalex.org/W4390532471","doi":"https://doi.org/10.1145/3632410.3632499","title":"Effect of dimensionality change on the bias of word embeddings","display_name":"Effect of dimensionality change on the bias of word embeddings","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390532471","doi":"https://doi.org/10.1145/3632410.3632499"},"language":"en","primary_location":{"id":"doi:10.1145/3632410.3632499","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","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/A5103014511","display_name":"Rohit Raj","orcid":"https://orcid.org/0009-0004-6002-1767"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rohit Raj Rai","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Guwahati, India"],"raw_orcid":"https://orcid.org/0009-0004-6002-1767","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000346770","display_name":"Amit Awekar","orcid":"https://orcid.org/0000-0003-1559-8247"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amit Awekar","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Guwahati, India"],"raw_orcid":"https://orcid.org/0000-0003-1559-8247","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103014511"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00199944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"602"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9976999759674072,"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/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.8994934558868408},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.7739184498786926},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7415022253990173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6819673776626587},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5967941880226135},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5801581144332886},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5686812996864319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5611234307289124},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44172051548957825},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17457059025764465}],"concepts":[{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.8994934558868408},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.7739184498786926},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7415022253990173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819673776626587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5967941880226135},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5801581144332886},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5686812996864319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5611234307289124},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44172051548957825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17457059025764465},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3632410.3632499","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2963691697","https://openalex.org/W2972413484"],"related_works":["https://openalex.org/W2946409105","https://openalex.org/W2607179749","https://openalex.org/W2905749112","https://openalex.org/W2985392712","https://openalex.org/W4388996947","https://openalex.org/W3152932816","https://openalex.org/W3101154008","https://openalex.org/W3099354896","https://openalex.org/W4287599800","https://openalex.org/W2890749918"],"abstract_inverted_index":{"Word":[0],"embedding":[1],"methods":[2],"(WEMs)":[3],"are":[4],"extensively":[5],"used":[6],"for":[7,62],"representing":[8],"text":[9],"data.":[10],"The":[11,22],"dimensionality":[12,25,41,93,103,119],"of":[13,24,30,46,88,108,120],"these":[14],"embeddings":[15,48,90],"varies":[16],"across":[17],"various":[18],"tasks":[19],"and":[20,66,68,72],"implementations.":[21],"effect":[23,61],"change":[26,42,104],"on":[27],"the":[28,31,40,44,54,86,92,102,106,118],"accuracy":[29],"downstream":[32],"task":[33],"is":[34,81,97],"a":[35,82],"well-explored":[36],"question.":[37],"However,":[38],"how":[39,101],"affects":[43,105],"bias":[45,87,107],"word":[47,89,109,121],"needs":[49],"to":[50],"be":[51,114],"investigated.":[52],"Using":[53],"English":[55],"Wikipedia":[56],"corpus,":[57],"we":[58],"study":[59],"this":[60],"two":[63,69,77],"static":[64],"(Word2Vec":[65],"fastText)":[67],"context-sensitive":[70],"(ElMo":[71],"BERT)":[73],"WEMs.":[74],"We":[75],"have":[76],"observations.":[78],"First,":[79],"there":[80,96],"significant":[83],"variation":[84],"in":[85,100],"with":[91],"change.":[94],"Second,":[95],"no":[98],"uniformity":[99],"embeddings.":[110,122],"These":[111],"factors":[112],"should":[113],"considered":[115],"while":[116],"selecting":[117]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}