{"id":"W3217747958","doi":"10.18280/isi.260506","title":"Impact of Using Bidirectional Encoder Representations from Transformers (BERT) Models for Arabic Dialogue Acts Identification","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Transformer; Natural language processing; Encoder; Artificial intelligence; Representation (politics); Utterance; Language model; Arabic; Identification (biology); Task (project management); Speech recognition; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002541666,0.0001246453,0.0001815614,0.0002023861,0.0001997488,0.0002295541,0.0002244437,0.0000884361,0.00001186894],"category_scores_gemma":[0.0001956898,0.0001277662,0.000174086,0.0004387656,0.0000420307,0.006171311,0.00003912356,0.00006710923,0.000004473306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003020289,"about_ca_system_score_gemma":0.0004018028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006565286,"about_ca_topic_score_gemma":0.00003782827,"domain_scores_codex":[0.9986007,0.00005223156,0.0006830299,0.0001975295,0.0002678837,0.0001986224],"domain_scores_gemma":[0.9985215,0.000139735,0.0003169863,0.0003282488,0.0006331666,0.00006038391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004372865,0.00008641936,0.002310284,0.0001937363,0.0002257125,0.000001104289,0.02304864,0.8229121,0.02398258,0.02290802,0.0001006637,0.104187],"study_design_scores_gemma":[0.000329688,0.00001765391,0.006529279,0.000055829,0.0000208913,0.00001276763,0.0002642221,0.9536516,0.008182105,0.03076653,0.00003251356,0.0001369184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2709687,0.00004518069,0.7277269,0.0000275045,0.0002921239,0.0001644948,0.00007422781,0.00005686551,0.000643944],"genre_scores_gemma":[0.9346573,0.00001718045,0.06489196,0.00002406863,0.00004923799,0.00004513293,0.0002877224,0.000006647047,0.00002072631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6636886,"threshold_uncertainty_score":0.5210153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0470122826845457,"score_gpt":0.2962686801892959,"score_spread":0.2492563975047502,"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."}}