{"id":"W1536638548","doi":"10.1007/978-3-642-14770-8_36","title":"Using Comparable Corpora to Improve the Effectiveness of Cross-Language Information Retrieval","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Natural language processing; Cross-language information retrieval; Terminology; Artificial intelligence; Information retrieval; Focus (optics); Selection (genetic algorithm); Machine translation; Point (geometry); Ambiguity; Text corpus; Linguistics","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":[0.01405272,0.002720782,0.00307429,0.01607631,0.003261031,0.006320552,0.003177009,0.002391314,0.02820555],"category_scores_gemma":[0.066834,0.001290571,0.001677514,0.01309584,0.001187869,0.01331173,0.006175163,0.002671713,0.01787547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00118223,"about_ca_system_score_gemma":0.002543165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00744028,"about_ca_topic_score_gemma":0.01123336,"domain_scores_codex":[0.9867322,0.006347775,0.001960056,0.002031205,0.002458633,0.0004700939],"domain_scores_gemma":[0.9545796,0.02400029,0.0009660532,0.009142322,0.01072053,0.000591227],"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":[0.001265394,0.001539725,0.005551967,0.005900684,0.001056351,0.001663079,0.001882955,0.00456237,0.05992252,0.01010166,0.1763222,0.730231],"study_design_scores_gemma":[0.00248636,0.002335532,0.02984845,0.003186433,0.005821525,0.006944537,0.006099789,0.1566087,0.1915961,0.0391015,0.5549099,0.001061158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2398787,0.03702585,0.4559774,0.006344114,0.01028114,0.004536229,0.0544185,0.05668675,0.1348512],"genre_scores_gemma":[0.3115772,0.008110849,0.4946266,0.002056466,0.001906951,0.001868552,0.1546447,0.006266161,0.01894257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02820555,"threshold_uncertainty_score":0.09435695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01460561007763163,"score_gpt":0.2992259525697489,"score_spread":0.2846203424921173,"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."}}