{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004384938,0.000970312,0.001201212,0.004949777,0.001508831,0.002034365,0.001708636,0.001089807,0.009304539],"category_scores_gemma":[0.01228721,0.0006691323,0.001260695,0.005296552,0.0008033365,0.00457086,0.002051438,0.001679489,0.007704584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007361212,"about_ca_system_score_gemma":0.001397331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001500833,"about_ca_topic_score_gemma":0.001991352,"domain_scores_codex":[0.9966127,0.001419234,0.0003398066,0.000695463,0.0008214319,0.0001113566],"domain_scores_gemma":[0.9911376,0.003733607,0.0006845661,0.002584385,0.00171291,0.0001469266],"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":[0.0003341811,0.0003538797,0.001658818,0.0004525029,0.0001289669,0.00042453,0.0003104421,0.01294979,0.01647418,0.01429324,0.01683254,0.9357869],"study_design_scores_gemma":[0.000226114,0.000311574,0.003550051,0.0001682046,0.0001546787,0.001672269,0.0004509379,0.6673937,0.06238588,0.1406763,0.1228717,0.000138599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01034395,0.0008992663,0.9682152,0.0005909474,0.0001684301,0.0004757715,0.0009109467,0.01461654,0.003778992],"genre_scores_gemma":[0.07798153,0.0005533483,0.9124344,0.0002178545,0.0001832319,0.0006337071,0.003293242,0.0007156985,0.003986985],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009304539,"threshold_uncertainty_score":0.03112686,"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."}}