{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006137402,0.0004102132,0.0002954344,0.0005487853,0.0003271909,0.0009034816,0.00432037,0.0003595788,0.00003966941],"category_scores_gemma":[0.0003249566,0.0002893183,0.0001097932,0.0006722798,0.0006178021,0.0009203049,0.0007132718,0.0008562055,0.0001730249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002338332,"about_ca_system_score_gemma":0.0005273086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001803441,"about_ca_topic_score_gemma":0.0000253407,"domain_scores_codex":[0.997047,0.00003233365,0.0005054558,0.0008269952,0.001150202,0.0004379839],"domain_scores_gemma":[0.9965121,0.001002898,0.0003710841,0.001848926,0.0001880986,0.00007691594],"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":[0.00002277313,0.0000245036,0.00009154261,0.000005599712,0.000005679289,0.00001341054,0.0004114416,0.04451856,0.00003014552,0.01567958,0.0002169587,0.9389798],"study_design_scores_gemma":[0.0004580078,0.0001404921,0.0004278537,0.0001636553,0.000004864393,0.000004917421,6.330976e-7,0.8874511,0.0009736514,0.08609017,0.02382891,0.0004557405],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002110705,0.0001177076,0.9875271,0.005567063,0.001104824,0.0004066291,0.00001258561,0.0004632652,0.004589738],"genre_scores_gemma":[0.7435855,0.0001138096,0.2469656,0.00839959,0.0004934423,0.00001669601,0.00004913013,0.00002925758,0.0003470683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9385241,"threshold_uncertainty_score":0.9999559,"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."}}