{"id":"https://openalex.org/W2892043975","doi":"https://doi.org/10.18653/v1/d18-1502","title":"Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models","display_name":"Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2892043975","doi":"https://doi.org/10.18653/v1/d18-1502","mag":"2892043975"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1502","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1502","pdf_url":"https://www.aclweb.org/anthology/D18-1502.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1502.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090551925","display_name":"Sedtawut Watcharawittayakul","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sedtawut Watcharawittayakul","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science Lassonde School of Engineering, York University 4700 Keele Street, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science Lassonde School of Engineering, York University 4700 Keele Street, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086280874","display_name":"Mingbin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mingbin Xu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science Lassonde School of Engineering, York University 4700 Keele Street, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science Lassonde School of Engineering, York University 4700 Keele Street, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science Lassonde School of Engineering, York University 4700 Keele Street, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science Lassonde School of Engineering, York University 4700 Keele Street, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":0.338,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69079535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4725","last_page":"4730"},"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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/forgetting","display_name":"Forgetting","score":0.8988336324691772},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7578225135803223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7348701357841492},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7106292843818665},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.6514230966567993},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5227339863777161},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4730070233345032},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.467853844165802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4428649842739105},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4119584858417511},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10820826888084412},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09565895795822144}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.8988336324691772},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7578225135803223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7348701357841492},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7106292843818665},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6514230966567993},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5227339863777161},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4730070233345032},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.467853844165802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4428649842739105},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4119584858417511},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10820826888084412},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09565895795822144},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1502","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1502","pdf_url":"https://www.aclweb.org/anthology/D18-1502.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1502","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1502","pdf_url":"https://www.aclweb.org/anthology/D18-1502.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2892043975.pdf","grobid_xml":"https://content.openalex.org/works/W2892043975.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1943583106","https://openalex.org/W2064675550","https://openalex.org/W2097732278","https://openalex.org/W2120861206","https://openalex.org/W2140679639","https://openalex.org/W2152790380","https://openalex.org/W2175585630","https://openalex.org/W2251640092","https://openalex.org/W2259472270","https://openalex.org/W2293997542","https://openalex.org/W2567070169","https://openalex.org/W2611669587","https://openalex.org/W2740006839","https://openalex.org/W2759604924","https://openalex.org/W2805217704","https://openalex.org/W2806889342","https://openalex.org/W2950797609","https://openalex.org/W2962819663","https://openalex.org/W2963970792","https://openalex.org/W2998704965","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2020757772","https://openalex.org/W2902731467"],"abstract_inverted_index":{"In":[0,63],"this":[1],"paper,":[2],"we":[3,66],"propose":[4],"a":[5],"new":[6],"approach":[7],"to":[8,34],"employ":[9],"the":[10,45,55,60,69,78,89,109,116,129],"fixed-size":[11],"ordinally-forgetting":[12],"encoding":[13],"(FOFE)":[14],"(Zhang":[15],"et":[16],"al.,":[17],"2015b)":[18],"in":[19,47,59,126],"neural":[20,72],"languages":[21],"modelling,":[22],"called":[23],"dual-FOFE.":[24],"The":[25],"main":[26],"idea":[27],"behind":[28],"dual-FOFE":[29,70,118],"is":[30],"that":[31,41,96],"it":[32,42],"allows":[33],"use":[35],"two":[36],"different":[37],"forgetting":[38,57],"factors":[39],"so":[40],"can":[43],"avoid":[44],"trade-off":[46],"choosing":[48],"either":[49],"small":[50],"or":[51],"large":[52],"values":[53],"for":[54],"single":[56],"factor":[58],"original":[61,79,130],"FOFE.":[62],"our":[64],"experiments,":[65],"have":[67],"compared":[68],"based":[71],"network":[73],"language":[74],"models":[75],"(NNLM)":[76],"against":[77],"FOFE":[80,98,101,131],"counterparts":[81],"and":[82,99],"various":[83],"traditional":[84],"NNLMs.":[85,114],"Our":[86],"results":[87],"on":[88],"challenging":[90],"Google":[91],"Billion":[92],"Words":[93],"corpus":[94],"show":[95],"both":[97],"dual":[100],"yield":[102],"very":[103],"strong":[104],"performance":[105],"while":[106],"significantly":[107],"reducing":[108],"computational":[110],"complexity":[111],"over":[112,122,128],"other":[113],"Furthermore,":[115],"proposed":[117],"method":[119],"further":[120],"gives":[121],"10%":[123],"relative":[124],"improvement":[125],"perplexity":[127],"model.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}