{"id":"W1718341272","doi":"10.1007/3-540-44645-1_18","title":"Multilingual Information Retrieval Based on Parallel Texts from the Web","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Clef; Machine translation; Information retrieval; Parallel corpora; Cross-language information retrieval; Artificial intelligence; Natural language processing; Task (project management); 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":[0.0006175537,0.0007286841,0.001160527,0.005651167,0.0009333516,0.002836638,0.0008019464,0.0007449794,0.009505312],"category_scores_gemma":[0.003822932,0.0004109768,0.0007217178,0.005264392,0.0005291636,0.006063631,0.001844693,0.0008480827,0.006155156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005176774,"about_ca_system_score_gemma":0.0006422042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00116363,"about_ca_topic_score_gemma":0.001802793,"domain_scores_codex":[0.9990733,0.0002891013,0.0001128384,0.0001753515,0.0002819242,0.00006751362],"domain_scores_gemma":[0.9984593,0.0008232333,0.00009640993,0.0001831707,0.0003719234,0.0000658749],"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":[0.00141016,0.0003546753,0.001065507,0.001306153,0.0001787612,0.0009322191,0.0005064256,0.007790829,0.06377114,0.0182503,0.02925394,0.87518],"study_design_scores_gemma":[0.0004775743,0.0007949994,0.005790822,0.0004976858,0.0009721275,0.003881411,0.001393551,0.50493,0.1855273,0.1263091,0.1690864,0.0003391619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.128259,0.01184901,0.7996215,0.001826739,0.0007977145,0.0004811405,0.004619722,0.01163063,0.04091455],"genre_scores_gemma":[0.4007663,0.007886554,0.545829,0.0004635899,0.001314479,0.0004403492,0.01520464,0.001242367,0.02685276],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009505312,"threshold_uncertainty_score":0.03179842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01887396000000883,"score_gpt":0.2507413725531626,"score_spread":0.2318674125531538,"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."}}