{"id":"W4385389006","doi":"10.18280/ria.370322","title":"Fine-Tuned IndoBERT Based Model and Data Augmentation for Indonesian Language Paraphrase Identification","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Paraphrase; Indonesian; Identification (biology); Natural language processing; Computer science; Artificial intelligence; Linguistics; Philosophy; Biology","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":[0.0007806439,0.0001390743,0.0001394013,0.0002470674,0.0001878471,0.0002465361,0.001122012,0.00007689736,0.000004870539],"category_scores_gemma":[0.0002589389,0.0001389416,0.00003490568,0.0007970083,0.0000505126,0.0007222216,0.0002979953,0.0001037211,0.00004095229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002556415,"about_ca_system_score_gemma":0.00005430957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002330006,"about_ca_topic_score_gemma":0.00004855125,"domain_scores_codex":[0.9985487,0.0000382075,0.0003489646,0.0006381159,0.0001701627,0.0002558808],"domain_scores_gemma":[0.9983882,0.0002048876,0.0001460656,0.001103983,0.00008931508,0.00006749357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008153066,0.0002100018,0.0003363978,0.0006022967,0.00003013981,0.00004130577,0.0061932,0.03146632,0.3133793,0.04908616,0.006576695,0.5919967],"study_design_scores_gemma":[0.00005019644,0.00002121355,0.00002488479,0.00004094488,0.000007196903,0.000003064148,0.0001271976,0.8115531,0.1776894,0.01027318,0.00007028245,0.0001392916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02106498,0.0003975474,0.9758223,0.001486088,0.0001039931,0.0004657943,0.00004126678,0.0005905803,0.00002745315],"genre_scores_gemma":[0.8603399,0.00001961723,0.1386414,0.0001411333,0.00003408994,0.00010576,0.0002884348,0.00001637362,0.000413327],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8392749,"threshold_uncertainty_score":0.5665873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06767984215524922,"score_gpt":0.3536898737640879,"score_spread":0.2860100316088388,"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."}}