{"id":"https://openalex.org/W2884670325","doi":"https://doi.org/10.18653/v1/p18-1172","title":"Batch IS NOT Heavy: Learning Word Representations From All Samples","display_name":"Batch IS NOT Heavy: Learning Word Representations From All Samples","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2884670325","doi":"https://doi.org/10.18653/v1/p18-1172","mag":"2884670325"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1172","pdf_url":"https://www.aclweb.org/anthology/P18-1172.pdf","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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1172.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100393241","display_name":"Xin Xin","orcid":"https://orcid.org/0000-0001-6116-9115"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xin Xin","raw_affiliation_strings":["School of Computing Science, University of Glasgow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081665927","display_name":"Fajie Yuan","orcid":"https://orcid.org/0000-0001-8452-9929"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fajie Yuan","raw_affiliation_strings":["School of Computing Science, University of Glasgow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038668215","display_name":"Xiangnan He","orcid":"https://orcid.org/0000-0001-8472-7992"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiangnan He","raw_affiliation_strings":["School of Computing, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069702331","display_name":"Joemon M. Jose","orcid":"https://orcid.org/0000-0001-9228-1759"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joemon M. Jose","raw_affiliation_strings":["School of Computing Science, University of Glasgow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1853","last_page":"1862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.998199999332428,"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":0.9980999827384949,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.7611655592918396},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6765877604484558},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6469694375991821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6139304637908936},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5649769306182861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5440766215324402},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.447835236787796},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4181489944458008},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41223689913749695},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3675679564476013},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.33211132884025574},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2810886800289154},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12394708395004272},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.07490867376327515}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7611655592918396},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6765877604484558},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6469694375991821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6139304637908936},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5649769306182861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5440766215324402},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.447835236787796},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4181489944458008},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41223689913749695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3675679564476013},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.33211132884025574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2810886800289154},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12394708395004272},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.07490867376327515},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p18-1172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1172","pdf_url":"https://www.aclweb.org/anthology/P18-1172.pdf","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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:162396","is_oa":true,"landing_page_url":"http://eprints.gla.ac.uk/view/author/43969.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/167277","is_oa":false,"landing_page_url":"https://scholarbank.nus.edu.sg/handle/10635/167277","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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 Paper"},{"id":"mag:2884670325","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/162396/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1172","pdf_url":"https://www.aclweb.org/anthology/P18-1172.pdf","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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2884670325.pdf","grobid_xml":"https://content.openalex.org/works/W2884670325.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2886144305","https://openalex.org/W2962997783","https://openalex.org/W2429473340","https://openalex.org/W3135804679","https://openalex.org/W2809657547","https://openalex.org/W3167827288","https://openalex.org/W3126908443","https://openalex.org/W3130183161","https://openalex.org/W2995758797","https://openalex.org/W2774769176","https://openalex.org/W2902200315","https://openalex.org/W3094458826","https://openalex.org/W2559118471","https://openalex.org/W2963691377","https://openalex.org/W171557998","https://openalex.org/W2950352605","https://openalex.org/W2788764574","https://openalex.org/W120376054","https://openalex.org/W2928169590","https://openalex.org/W2955260427"],"abstract_inverted_index":{"Stochastic":[0],"Gradient":[1],"Descent":[2],"(SGD)":[3],"with":[4,107],"negative":[5],"sampling":[6,21,28],"is":[7,18],"the":[8,27,32,44,68,75,83],"most":[9],"prevalent":[10],"approach":[11],"to":[12,43,59],"learn":[13],"word":[14,61],"representations.":[15],"However,":[16],"it":[17],"known":[19],"that":[20,54,101],"methods":[22,106],"are":[23],"biased":[24],"especially":[25,110],"when":[26],"distribution":[29],"deviates":[30],"from":[31,39,63],"true":[33],"data":[34],"distribution.":[35],"Besides,":[36],"SGD":[37,105],"suffers":[38],"dramatic":[40],"fluctuation":[41],"due":[42],"onesample":[45],"learning":[46,58],"scheme.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"propose":[52],"AllVec":[53,72,94,102],"uses":[55],"batch":[56],"gradient":[57],"generate":[60],"representations":[62],"all":[64,90],"training":[65,113],"samples.":[66,91],"Remarkably,":[67],"time":[69],"complexity":[70],"of":[71,85],"remains":[73],"at":[74],"same":[76],"level":[77],"as":[78],"SGD,":[79],"being":[80],"determined":[81],"by":[82],"number":[84],"positive":[86],"samples":[87],"rather":[88],"than":[89],"We":[92],"evaluate":[93],"on":[95],"several":[96],"benchmark":[97],"tasks.":[98],"Experiments":[99],"show":[100],"outperforms":[103],"samplingbased":[104],"comparable":[108],"efficiency,":[109],"for":[111],"small":[112],"corpora.":[114]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}