{"id":"W200075660","doi":"","title":"Parallel web text mining for cross-language IR","year":2000,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Machine translation; Parallel corpora; Web mining; Cross-language information retrieval; Natural language processing; Information retrieval; Artificial intelligence; Data mining; Web service; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001984073,0.000131145,0.0001265544,0.00006193799,0.0001314772,0.000351463,0.0009854193,0.00007904555,0.0003572097],"category_scores_gemma":[0.00004666535,0.0001046172,0.00006784833,0.0002161693,0.00003990241,0.0005665512,0.00009832756,0.00008509277,0.00006768649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002327608,"about_ca_system_score_gemma":0.00004588212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001799053,"about_ca_topic_score_gemma":0.000008738428,"domain_scores_codex":[0.9989806,0.00001493806,0.0001761184,0.0003572869,0.000156737,0.0003143415],"domain_scores_gemma":[0.9993071,0.00009192147,0.00004063325,0.0004432594,0.00005183388,0.00006526561],"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":[0.00003098513,0.0000614369,0.0002880129,0.00004747906,0.00001430788,0.00003772543,0.002032377,0.00002413979,0.006454265,0.03922785,0.01874376,0.9330376],"study_design_scores_gemma":[0.0050176,0.0009266188,0.001291822,0.0003134001,0.00003540612,0.0003631729,0.0003880631,0.4982522,0.189222,0.1028936,0.1978439,0.003452199],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06749145,0.002768943,0.8995648,0.001153906,0.0001347661,0.0004011025,0.000005747404,0.002844384,0.02563493],"genre_scores_gemma":[0.2577067,0.000006020795,0.7266953,0.0009102154,0.00006279969,0.00003502516,0.000002463952,0.00001014547,0.01457133],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9295855,"threshold_uncertainty_score":0.4266164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01305078358880081,"score_gpt":0.3073651442071318,"score_spread":0.294314360618331,"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."}}