{"id":"https://openalex.org/W7117296775","doi":"https://doi.org/10.1007/s42979-025-04612-y","title":"HmBlogs: A Comprehensive Corpus and Benchmarking Study for Persian Word Embedding and Language Modeling","display_name":"HmBlogs: A Comprehensive Corpus and Benchmarking Study for Persian Word Embedding and Language Modeling","publication_year":2025,"publication_date":"2025-12-26","ids":{"openalex":"https://openalex.org/W7117296775","doi":"https://doi.org/10.1007/s42979-025-04612-y"},"language":"en","primary_location":{"id":"doi:10.1007/s42979-025-04612-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42979-025-04612-y","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","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/A5023914076","display_name":"Hamzeh Motahari Khansari","orcid":null},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hamzeh Motahari Khansari","raw_affiliation_strings":["NLP Research Lab, Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLP Research Lab, Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran","institution_ids":["https://openalex.org/I48379061"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085075919","display_name":"Mehrnoush ShamsFard","orcid":null},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Mehrnoush Shamsfard","raw_affiliation_strings":["Computer Engineering Department, Sharif University of Technology, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0002-7027-7529","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093917442","display_name":"Mostafa Masumi","orcid":null},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mostafa Masumi","raw_affiliation_strings":["NLP Research Lab, Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLP Research Lab, Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran","institution_ids":["https://openalex.org/I48379061"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093917443","display_name":"Seyed Soroush Majd","orcid":null},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Seyed Soroush Majd","raw_affiliation_strings":["NLP Research Lab, Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLP Research Lab, Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran","institution_ids":["https://openalex.org/I48379061"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085075919"],"corresponding_institution_ids":["https://openalex.org/I133529467"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74223431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","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":0.7468000054359436,"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":0.7468000054359436,"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":0.07339999824762344,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.026599999517202377,"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/analogy","display_name":"Analogy","score":0.8456000089645386},{"id":"https://openalex.org/keywords/persian","display_name":"Persian","score":0.6173999905586243},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6137999892234802},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5882999897003174},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5874999761581421},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.46549999713897705},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43130001425743103},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4156999886035919}],"concepts":[{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.8456000089645386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7651000022888184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758400022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6484000086784363},{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6137999892234802},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5882999897003174},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s42979-025-04612-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42979-025-04612-y","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4348916709423065}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W2026306693","https://openalex.org/W2044565013","https://openalex.org/W2132585910","https://openalex.org/W2214534013","https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2753628379","https://openalex.org/W2786010334","https://openalex.org/W2892839738","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W3015397590","https://openalex.org/W3032299950","https://openalex.org/W3087094142","https://openalex.org/W3161429121","https://openalex.org/W3175124037","https://openalex.org/W3212310951","https://openalex.org/W3213458975","https://openalex.org/W4221165895","https://openalex.org/W4288028050","https://openalex.org/W4293824282","https://openalex.org/W4318035574","https://openalex.org/W4385627225","https://openalex.org/W4386875581","https://openalex.org/W4387891332","https://openalex.org/W4387929273","https://openalex.org/W4388486382","https://openalex.org/W4389501301","https://openalex.org/W4391767116","https://openalex.org/W4399399473","https://openalex.org/W4407692460","https://openalex.org/W4407951893"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-02-06T02:01:19.302388","created_date":"2025-12-26T00:00:00"}
