{"id":"W622962318","doi":"10.71781/11078","title":"Recherche d'information translinguistique sur les documents en arabe","year":2008,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Cross-language information retrieval; Artificial intelligence; Arabic; Context (archaeology); Machine translation; Information retrieval; Word (group theory); Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001603617,0.0004939654,0.000486471,0.000227013,0.0003651402,0.001652812,0.003342625,0.001245487,0.0005321094],"category_scores_gemma":[0.001517663,0.000494881,0.0001398689,0.0005865959,0.00006788941,0.003864367,0.0002593876,0.001432513,0.0005754902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003573708,"about_ca_system_score_gemma":0.001057092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003451986,"about_ca_topic_score_gemma":0.0009693868,"domain_scores_codex":[0.9970537,0.0005667053,0.0008074059,0.0006186529,0.0005116855,0.0004418023],"domain_scores_gemma":[0.9974352,0.0003857256,0.000607857,0.0006160879,0.0008150554,0.0001400415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005516958,0.00007136675,0.0000266725,0.0001616341,0.00003868686,0.00004291625,0.04611748,0.000007424085,0.001030514,0.001315048,0.0007908227,0.9503422],"study_design_scores_gemma":[0.001439399,0.0004027608,0.0003508063,0.004309013,0.0001691562,0.0002567399,0.001929755,0.009051298,0.4469872,0.01488461,0.5177786,0.002440594],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08926206,0.03039559,0.6188404,0.003934331,0.005750798,0.007463335,0.00026265,0.000232122,0.2438587],"genre_scores_gemma":[0.02929246,0.0008766568,0.9448356,0.0001262136,0.0001526334,0.00008945389,0.001001381,0.000033372,0.02359224],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9479017,"threshold_uncertainty_score":0.9997503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1255534000594949,"score_gpt":0.3917661871829478,"score_spread":0.2662127871234529,"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."}}