{"id":"W2118195382","doi":"10.3115/1220175.1220231","title":"Semi-supervised learning of partial cognates using bilingual bootstrapping","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Natural language processing; Bootstrapping (finance); Artificial intelligence; Context (archaeology); Meaning (existential); Cognate; Machine translation; Labeled data; Supervised learning; Linguistics; Mathematics; Artificial neural network; Psychology","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":[0.0002472514,0.0001214731,0.0001653253,0.0001248157,0.0001001445,0.00009772793,0.0004752353,0.00007385222,0.00001855236],"category_scores_gemma":[0.00006632927,0.0001048161,0.00005870535,0.0003850237,0.0000528157,0.000381375,0.0001833173,0.0001741148,0.000002077212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000231984,"about_ca_system_score_gemma":0.00009237642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004239226,"about_ca_topic_score_gemma":0.000005800789,"domain_scores_codex":[0.9989191,0.00004886157,0.0002820592,0.0002735851,0.0002310414,0.000245348],"domain_scores_gemma":[0.999447,0.00007499882,0.0001178417,0.0002105784,0.0001178063,0.00003177832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009505747,0.00009000866,0.00591543,0.00009622553,0.00001797903,0.00003783015,0.0006084219,0.00290976,0.8815371,0.0859715,0.00008346133,0.0227228],"study_design_scores_gemma":[0.0001298386,0.00003141307,0.00004823523,0.00005913425,0.000005209118,0.00001559346,0.00003449676,0.3831482,0.6098116,0.006472826,0.00009016816,0.0001532657],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.238499,0.0008111959,0.7591166,0.00005664553,0.00005751299,0.00006759376,3.262117e-7,0.0006250682,0.0007660352],"genre_scores_gemma":[0.6858873,0.000001353103,0.3139307,0.00002915214,0.0000511387,9.176125e-7,0.000001343924,0.000006580148,0.0000914801],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4473883,"threshold_uncertainty_score":0.4274276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01800472544288471,"score_gpt":0.2751417126019726,"score_spread":0.2571369871590879,"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."}}