{"id":"W2252107976","doi":"10.63317/4ts6k3m8qm7t","title":"An Iterative Approach for Mining Parallel Sentences in a Comparable Corpus","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Machine translation; Sentence; Bootstrapping (finance); Classifier (UML); Natural language processing; Artificial intelligence; Focus (optics); Parallel corpora","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005120638,0.001434485,0.001427229,0.007601019,0.002370827,0.003069422,0.003528669,0.00183023,0.007208447],"category_scores_gemma":[0.02505011,0.001246252,0.001990117,0.006874331,0.001196631,0.004007243,0.003748377,0.002505278,0.003878584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008689062,"about_ca_system_score_gemma":0.005202767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004563823,"about_ca_topic_score_gemma":0.01115199,"domain_scores_codex":[0.9934061,0.001805538,0.000917867,0.001997539,0.00163971,0.0002332088],"domain_scores_gemma":[0.9799553,0.01094672,0.0009086811,0.002477226,0.005341171,0.0003711093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008831174,0.000873842,0.008102516,0.001989779,0.0006910899,0.001759324,0.003595884,0.008737008,0.08459437,0.02110161,0.01912669,0.8485447],"study_design_scores_gemma":[0.0006099489,0.001898337,0.02142884,0.000611765,0.002407204,0.006616104,0.005484546,0.6107505,0.1002302,0.1256779,0.1238359,0.0004487639],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03574333,0.0006837206,0.9497136,0.0004262604,0.0001536843,0.001456209,0.00312089,0.004932338,0.003769862],"genre_scores_gemma":[0.07518191,0.0002335713,0.9128155,0.000152674,0.0001183419,0.0008358928,0.007629266,0.0004543368,0.002578403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007601019,"threshold_uncertainty_score":0.02708083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02557996846621315,"score_gpt":0.2952854227501761,"score_spread":0.269705454283963,"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."}}