{"id":"https://openalex.org/W4399244286","doi":"https://doi.org/10.1007/s13042-024-02132-4","title":"Pretraining without wordpieces: learning over a vocabulary of millions of words","display_name":"Pretraining without wordpieces: learning over a vocabulary of millions of words","publication_year":2024,"publication_date":"2024-05-31","ids":{"openalex":"https://openalex.org/W4399244286","doi":"https://doi.org/10.1007/s13042-024-02132-4"},"language":"en","primary_location":{"id":"doi:10.1007/s13042-024-02132-4","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1007/s13042-024-02132-4","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-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/A5007059246","display_name":"Zhangyin Feng","orcid":"https://orcid.org/0000-0001-5909-1339"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangyin Feng","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0001-5909-1339","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110628758","display_name":"Duyu Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duyu Tang","raw_affiliation_strings":["Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073213620","display_name":"Xiaocheng Feng","orcid":"https://orcid.org/0000-0001-6011-0496"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaocheng Feng","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China","Peng Cheng Laboratory, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101146933","display_name":"Cong Zhou","orcid":"https://orcid.org/0009-0008-4582-4122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Zhou","raw_affiliation_strings":["Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078591720","display_name":"Junwei Liao","orcid":"https://orcid.org/0000-0001-7321-7583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junwei Liao","raw_affiliation_strings":["Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091839641","display_name":"Shuangzhi Wu","orcid":"https://orcid.org/0000-0002-6371-9720"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuangzhi Wu","raw_affiliation_strings":["Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017671620","display_name":"Bing Qin","orcid":"https://orcid.org/0000-0002-2543-5604"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Qin","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China","Peng Cheng Laboratory, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011542448","display_name":"Yunbo Cao","orcid":"https://orcid.org/0009-0005-2558-5206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunbo Cao","raw_affiliation_strings":["Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087920747","display_name":"Shuming Shi","orcid":"https://orcid.org/0000-0001-7018-0682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuming Shi","raw_affiliation_strings":["Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5073213620"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210136793"],"apc_list":{"value":2790,"currency":"EUR","value_usd":3590},"apc_paid":null,"fwci":0.3311,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62568834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"15","issue":"9","first_page":"3989","last_page":"3998"},"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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/computational-intelligence","display_name":"Computational intelligence","score":0.7502230405807495},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7170364260673523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.54930180311203},{"id":"https://openalex.org/keywords/vocabulary-learning","display_name":"Vocabulary learning","score":0.5247804522514343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.516395628452301},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48326951265335083},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4193878471851349},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0855800211429596}],"concepts":[{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.7502230405807495},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7170364260673523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.54930180311203},{"id":"https://openalex.org/C2984601542","wikidata":"https://www.wikidata.org/wiki/Q48842322","display_name":"Vocabulary learning","level":3,"score":0.5247804522514343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.516395628452301},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48326951265335083},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4193878471851349},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0855800211429596}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13042-024-02132-4","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1007/s13042-024-02132-4","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3989179862","display_name":null,"funder_award_id":"62276078","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6060587251","display_name":null,"funder_award_id":"2020AAA0106502","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7930149284","display_name":null,"funder_award_id":"62276078","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1981276685","https://openalex.org/W2064675550","https://openalex.org/W2250539671","https://openalex.org/W2889048825","https://openalex.org/W2952370363","https://openalex.org/W2962739339","https://openalex.org/W2963323070","https://openalex.org/W2963748441","https://openalex.org/W2971039193","https://openalex.org/W3034999214","https://openalex.org/W3114651185","https://openalex.org/W3169113923","https://openalex.org/W3175212568","https://openalex.org/W4387428045","https://openalex.org/W6600424091","https://openalex.org/W6601211009","https://openalex.org/W6780161852"],"related_works":["https://openalex.org/W3019875293","https://openalex.org/W2351746492","https://openalex.org/W2367621846","https://openalex.org/W2394096350","https://openalex.org/W2091742426","https://openalex.org/W2365662948","https://openalex.org/W1988910916","https://openalex.org/W2380430606","https://openalex.org/W4360597343","https://openalex.org/W4287151890"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-21T23:30:37.877113","created_date":"2025-10-10T00:00:00"}
