{"id":"https://openalex.org/W4416776198","doi":"https://doi.org/10.1007/s41060-025-00955-0","title":"Statistical interpretation for word embeddings in natural language processing","display_name":"Statistical interpretation for word embeddings in natural language processing","publication_year":2025,"publication_date":"2025-11-28","ids":{"openalex":"https://openalex.org/W4416776198","doi":"https://doi.org/10.1007/s41060-025-00955-0"},"language":"en","primary_location":{"id":"doi:10.1007/s41060-025-00955-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s41060-025-00955-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","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/A5002975981","display_name":"Zitong Zhang","orcid":"https://orcid.org/0000-0003-3123-1509"},"institutions":[{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zitong Zhang","raw_affiliation_strings":["Department of Environmental Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Environmental Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA","institution_ids":["https://openalex.org/I98704320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035675158","display_name":"Ashraf Yaseen","orcid":"https://orcid.org/0000-0002-0598-3419"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashraf Yaseen","raw_affiliation_strings":["Department of Biostatistics, University of Texas Health Science Center at Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, University of Texas Health Science Center at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045155778","display_name":"Hulin Wu","orcid":"https://orcid.org/0000-0002-5809-5407"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hulin Wu","raw_affiliation_strings":["Department of Biostatistics, University of Texas Health Science Center at Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, University of Texas Health Science Center at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002975981"],"corresponding_institution_ids":["https://openalex.org/I98704320"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2029874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.263700008392334,"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":0.263700008392334,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.12409999966621399,"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":0.08739999681711197,"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/word2vec","display_name":"Word2vec","score":0.7738999724388123},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.7034000158309937},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.628000020980835},{"id":"https://openalex.org/keywords/pointwise-mutual-information","display_name":"Pointwise mutual information","score":0.6139000058174133},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.41190001368522644},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3885999917984009},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.38280001282691956},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.37940001487731934},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.3776000142097473},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.36419999599456787}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.7738999724388123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7105000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7080000042915344},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.7034000158309937},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6815999746322632},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.628000020980835},{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.6139000058174133},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3885999917984009},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.31700000166893005},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.302700012922287},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C2983335612","wikidata":"https://www.wikidata.org/wiki/Q54277","display_name":"Word processing","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s41060-025-00955-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s41060-025-00955-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1615991656","https://openalex.org/W1978400666","https://openalex.org/W2004026774","https://openalex.org/W2093641143","https://openalex.org/W4399469274","https://openalex.org/W7083595088"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-28T23:14:17.795251","created_date":"2025-11-28T00:00:00"}