{"id":"W2017180565","doi":"10.3115/974147.974151","title":"Automatic construction of parallel English-Chinese corpus for cross-language information retrieval","year":2000,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Parallel corpora; Natural language processing; Machine translation; Cross-language information retrieval; Artificial intelligence; Obstacle; Probabilistic logic; Information retrieval; Translation (biology); Language model","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":[0.00308565,0.001127737,0.001464517,0.003858005,0.002364002,0.001532489,0.001291174,0.0006646579,0.01325719],"category_scores_gemma":[0.01131082,0.0009233694,0.0009385018,0.004570954,0.0008804863,0.00358223,0.002352379,0.00162137,0.005330273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001536554,"about_ca_system_score_gemma":0.004799434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009248594,"about_ca_topic_score_gemma":0.01097743,"domain_scores_codex":[0.9975631,0.0008533963,0.0003009384,0.0005493049,0.0005759802,0.0001572336],"domain_scores_gemma":[0.9942307,0.001911987,0.0002327396,0.0009845623,0.00247714,0.0001628209],"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":[0.001172018,0.0008623335,0.004928815,0.002279378,0.0002023305,0.001700425,0.002054953,0.02247319,0.1044708,0.05227283,0.1200676,0.6875153],"study_design_scores_gemma":[0.0007680109,0.0006297191,0.0135118,0.0003623111,0.000583103,0.00202068,0.001934043,0.4315218,0.1915994,0.0499055,0.3068246,0.0003390926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09120852,0.00184249,0.8523216,0.001470677,0.0009623846,0.002081464,0.01529448,0.0142104,0.02060803],"genre_scores_gemma":[0.2527108,0.0009083406,0.6800015,0.0003591154,0.0003337418,0.003562467,0.05007744,0.002153144,0.009893547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01325719,"threshold_uncertainty_score":0.04434979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004689176591397629,"score_gpt":0.2683774311622606,"score_spread":0.263688254570863,"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."}}