{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008426444,0.001325224,0.0009167551,0.0008251632,0.0003861245,0.0009334605,0.002143549,0.001063315,0.003403832],"category_scores_gemma":[0.00318224,0.0004280932,0.001470444,0.0007105552,0.0003373905,0.002129955,0.001042394,0.002228974,0.002327447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008067176,"about_ca_system_score_gemma":0.0009225726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008720703,"about_ca_topic_score_gemma":0.01275301,"domain_scores_codex":[0.9994823,0.0000994627,0.00004853281,0.0002226987,0.00009551962,0.00005148377],"domain_scores_gemma":[0.9989828,0.0003155334,0.00006133986,0.0003055359,0.0002889533,0.00004579302],"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":[0.000969196,0.0009700514,0.006032818,0.0004791192,0.0003016997,0.0005878112,0.0002818338,0.2421329,0.04044497,0.002555901,0.01945399,0.6857896],"study_design_scores_gemma":[0.00003124571,0.0001931814,0.001192845,0.00002866942,0.00005428512,0.0001836563,0.00004563725,0.9769889,0.014821,0.001521701,0.00490741,0.00003160073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2660651,0.002976349,0.6876776,0.001097613,0.0005855646,0.0006241066,0.005540603,0.02479902,0.0106341],"genre_scores_gemma":[0.6906434,0.000721276,0.2813784,0.0006235465,0.0001271559,0.0006797241,0.01230531,0.0006439658,0.01287722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008720703,"threshold_uncertainty_score":0.01733989,"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."}}