{"id":"https://openalex.org/W3127869043","doi":"https://doi.org/10.1145/3443279.3443304","title":"A Comparative Study on Word Embeddings in Deep Learning for Text Classification","display_name":"A Comparative Study on Word Embeddings in Deep Learning for Text Classification","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3127869043","doi":"https://doi.org/10.1145/3443279.3443304","mag":"3127869043"},"language":"en","primary_location":{"id":"doi:10.1145/3443279.3443304","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3443279.3443304","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3443279.3443304","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3443279.3443304","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100358611","display_name":"Congcong Wang","orcid":"https://orcid.org/0000-0002-5661-8796"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Congcong Wang","raw_affiliation_strings":["School of Computer Science, University College Dublin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Paul Nulty","orcid":null},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Paul Nulty","raw_affiliation_strings":["School of Computer Science, University College Dublin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037769267","display_name":"David Lillis","orcid":"https://orcid.org/0000-0002-5702-4463"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"David Lillis","raw_affiliation_strings":["School of Computer Science, University College Dublin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100358611"],"corresponding_institution_ids":["https://openalex.org/I100930933"],"apc_list":null,"apc_paid":null,"fwci":7.6161,"has_fulltext":true,"cited_by_count":108,"citation_normalized_percentile":{"value":0.9785779,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8242875337600708},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7547042369842529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6619881391525269},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6206573247909546},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6180168390274048},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5943362712860107},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5897495746612549},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5649839639663696},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5416164994239807},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.539450466632843},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4919257164001465},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.46267932653427124},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4614800810813904},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3526540696620941},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09697359800338745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09277895092964172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242875337600708},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7547042369842529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6619881391525269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6206573247909546},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6180168390274048},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5943362712860107},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5897495746612549},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5649839639663696},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5416164994239807},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.539450466632843},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4919257164001465},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.46267932653427124},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4614800810813904},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3526540696620941},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09697359800338745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09277895092964172},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3443279.3443304","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3443279.3443304","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3443279.3443304","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:researchrepository.ucd.ie:10197/25812","is_oa":false,"landing_page_url":"http://hdl.handle.net/10197/25812","pdf_url":null,"source":{"id":"https://openalex.org/S4306402280","display_name":"Research Repository UCD (University College Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I100930933","host_organization_name":"University College Dublin","host_organization_lineage":["https://openalex.org/I100930933"],"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":"Conference Publication"}],"best_oa_location":{"id":"doi:10.1145/3443279.3443304","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3443279.3443304","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3443279.3443304","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8850937825","display_name":null,"funder_award_id":"713654","funder_id":"https://openalex.org/F4320320834","funder_display_name":"Enterprise Ireland"}],"funders":[{"id":"https://openalex.org/F4320320834","display_name":"Enterprise Ireland","ror":"https://ror.org/023z51242"},{"id":"https://openalex.org/F4320320858","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3127869043.pdf","grobid_xml":"https://content.openalex.org/works/W3127869043.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W1832693441","https://openalex.org/W2020018978","https://openalex.org/W2064675550","https://openalex.org/W2091879664","https://openalex.org/W2094934653","https://openalex.org/W2153579005","https://openalex.org/W2170240176","https://openalex.org/W2250539671","https://openalex.org/W2251253014","https://openalex.org/W2251803266","https://openalex.org/W2251939518","https://openalex.org/W2296283641","https://openalex.org/W2493916176","https://openalex.org/W2740711318","https://openalex.org/W2771472444","https://openalex.org/W2793978524","https://openalex.org/W2880875857","https://openalex.org/W2887428522","https://openalex.org/W2947838898","https://openalex.org/W2950813464","https://openalex.org/W2962739339","https://openalex.org/W2963248507","https://openalex.org/W2963403868","https://openalex.org/W2963691697","https://openalex.org/W2964236337","https://openalex.org/W2980708516","https://openalex.org/W2983965928","https://openalex.org/W2996428491","https://openalex.org/W3088524223","https://openalex.org/W4365799947"],"related_works":["https://openalex.org/W2590462354","https://openalex.org/W2997627311","https://openalex.org/W2171469118","https://openalex.org/W4296501933","https://openalex.org/W3043161732","https://openalex.org/W2580878117","https://openalex.org/W2550523331","https://openalex.org/W2947963870","https://openalex.org/W1889584887","https://openalex.org/W2997152654"],"abstract_inverted_index":{"Word":[0],"embeddings":[1,68,101,179],"act":[2],"as":[3,19,132,164,169],"an":[4,229],"important":[5],"component":[6],"of":[7,32,47,72,99,166,176],"deep":[8],"models":[9],"for":[10,39,69,142,153,219,232],"providing":[11],"input":[12],"features":[13],"in":[14,90,138,160,192,198,241],"downstream":[15,92,134],"language":[16],"tasks,":[17],"such":[18],"sequence":[20,78,161],"labelling":[21],"and":[22,49,65,88,119,208],"text":[23,73],"classification.":[24,74],"In":[25,53],"the":[26,45,70,91,97,133,158,236],"last":[27],"decade,":[28],"a":[29,77,188,195],"substantial":[30],"number":[31],"word":[33,51,67,80,100,173],"embedding":[34],"methods":[35],"have":[36],"been":[37],"proposed":[38],"this":[40,54],"purpose,":[41],"mainly":[42],"falling":[43],"into":[44],"categories":[46],"classic":[48,64,178,225],"context-based":[50,202],"embeddings.":[52],"paper,":[55],"we":[56,82,105,204],"conduct":[57],"controlled":[58],"experiments":[59],"to":[60,187],"systematically":[61],"examine":[62],"both":[63,117,206,227],"contextualised":[66],"purposes":[71],"To":[75,95],"encode":[76],"from":[79],"representations,":[81],"apply":[83],"two":[84],"encoders,":[85],"namely":[86],"CNN":[87,131,150],"BiLSTM,":[89],"network":[93],"architecture.":[94],"study":[96,147],"impact":[98],"on":[102],"different":[103],"datasets,":[104],"select":[106],"four":[107],"benchmarking":[108],"classification":[109,121,155],"datasets":[110,156,234],"with":[111,126,224],"varying":[112],"average":[113],"sample":[114],"length,":[115],"comprising":[116],"single-label":[118],"multi-label":[120],"tasks.":[122],"The":[123,210],"evaluation":[124],"results":[125,211],"confidence":[127],"intervals":[128],"indicate":[129],"that":[130,213],"encoder":[135],"outperforms":[136,216],"BiLSTM":[137,152],"most":[139],"situations,":[140],"especially":[141,218],"document":[143,154,221],"context-insensitive":[144],"datasets.":[145,171,222,243],"This":[146],"recommends":[148],"choosing":[149],"over":[151],"where":[157],"context":[159],"is":[162,238],"not":[163,185,239],"indicative":[165],"class":[167],"membership":[168],"sentence":[170],"For":[172,201],"embeddings,":[174,203,226],"concatenation":[175],"multiple":[177],"or":[180],"increasing":[181],"their":[182],"size":[183],"does":[184],"lead":[186],"statistically":[189],"significant":[190],"difference":[191],"performance":[193,231],"despite":[194],"slight":[196],"improvement":[197,237],"some":[199],"cases.":[200],"studied":[205],"ELMo":[207],"BERT.":[209],"show":[212],"BERT":[214],"overall":[215],"ELMo,":[217],"long":[220],"Compared":[223],"achieve":[228],"improved":[230],"short":[233],"while":[235],"observed":[240],"longer":[242]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}