{"id":"W2141325213","doi":"10.1109/icsmc.2001.969854","title":"Filtering noisy parallel corpora of web pages","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Parallel corpora; Translation (biology); Machine translation; Natural language processing; Artificial intelligence; Information retrieval; Web page; World Wide Web","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":[0.006383431,0.001791141,0.00353949,0.006430579,0.002476809,0.002442493,0.001472771,0.001759891,0.003907894],"category_scores_gemma":[0.0328483,0.001653246,0.001789039,0.009302962,0.001368041,0.003792907,0.002487526,0.002264133,0.004466372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008713155,"about_ca_system_score_gemma":0.001667468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003029977,"about_ca_topic_score_gemma":0.005008447,"domain_scores_codex":[0.9906963,0.002597609,0.001153361,0.001758534,0.003423085,0.0003710113],"domain_scores_gemma":[0.9749708,0.01245857,0.001675986,0.004561984,0.006102819,0.0002298781],"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":[0.003759225,0.0009343771,0.01384497,0.004160136,0.0009299317,0.006187995,0.003023965,0.05256272,0.1514624,0.01083437,0.04851049,0.7037895],"study_design_scores_gemma":[0.0005018083,0.0008922363,0.03091717,0.0004011026,0.001180675,0.00604619,0.002158575,0.532522,0.2506129,0.03866563,0.1357356,0.0003660854],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2642702,0.005237842,0.7026573,0.001548296,0.001581661,0.0008195179,0.005395269,0.01239938,0.006090594],"genre_scores_gemma":[0.4100993,0.003146835,0.5348418,0.0009041772,0.001451462,0.00157726,0.03089886,0.003072769,0.01400747],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006430579,"threshold_uncertainty_score":0.03375924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0297197218768101,"score_gpt":0.243206128264564,"score_spread":0.2134864063877539,"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."}}