{"id":"W4403740969","doi":"10.1016/j.eswa.2024.125589","title":"FRGEM: Feature integration pre-training based Gaussian embedding model for Chinese word representation","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Sichuan Province Science and Technology Support Program; National University's Basic Research Foundation of China; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Word embedding; Feature (linguistics); Word (group theory); Artificial intelligence; Representation (politics); Embedding; Training (meteorology); Natural language processing; Pattern recognition (psychology); Gaussian; Training set; Machine learning; Mathematics; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002257113,0.0001962619,0.0001775985,0.0002080843,0.0002494025,0.0006835026,0.0005198439,0.000110193,0.000001032282],"category_scores_gemma":[0.00003726254,0.0001377215,0.00006088236,0.0008164768,0.00002644627,0.0007482926,0.00004189455,0.0001771091,0.0000036466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000109343,"about_ca_system_score_gemma":0.0001536923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004307135,"about_ca_topic_score_gemma":0.00001887001,"domain_scores_codex":[0.9986679,0.00003224225,0.0002332065,0.000595945,0.0002529909,0.0002177239],"domain_scores_gemma":[0.9989123,0.0001455439,0.0001066036,0.0006103275,0.0001502318,0.00007496914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000901127,0.0001730588,0.0001060569,0.001004354,0.0001406241,0.00001532892,0.04766372,0.03630684,0.05956988,0.5520567,0.02775007,0.2751233],"study_design_scores_gemma":[0.00010467,0.00001938041,0.000006768179,0.0003266023,0.000006576015,0.00001858434,0.0001677889,0.9913455,0.001269626,0.00466382,0.001880528,0.0001901075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009338115,0.003437089,0.9910638,0.001863917,0.0001338383,0.001533342,0.00001251413,0.001666354,0.0001957651],"genre_scores_gemma":[0.4819137,0.000003100854,0.5129086,0.0000850009,0.0001717726,0.004269931,0.00005898775,0.00002153371,0.0005672704],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9550387,"threshold_uncertainty_score":0.6591032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02342659784660859,"score_gpt":0.3473184360831819,"score_spread":0.3238918382365732,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}