{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002496745,0.0001137396,0.000156614,0.0001083128,0.00007076213,0.0001848179,0.0004808275,0.00008887352,0.0001296419],"category_scores_gemma":[0.0003006112,0.00008806623,0.00006280307,0.0003609364,0.00007150468,0.002092989,0.00004991473,0.00008378806,0.000009783204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003011513,"about_ca_system_score_gemma":0.0000484046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002443305,"about_ca_topic_score_gemma":0.000001549388,"domain_scores_codex":[0.9991035,0.00001880517,0.0003623124,0.0001382344,0.0002167599,0.0001603619],"domain_scores_gemma":[0.999117,0.00009099203,0.0001620456,0.0003272153,0.0002624621,0.00004024197],"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":[0.0001116655,0.00004943602,0.00102832,0.0003219529,0.00002207322,0.000002424688,0.007738546,0.0000610083,0.001484775,0.06217736,0.000494921,0.9265075],"study_design_scores_gemma":[0.003881394,0.0006744619,0.003827942,0.0001966663,0.00003107821,0.0001782386,0.0003132532,0.7249463,0.1154494,0.1465725,0.002815231,0.001113466],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3778865,0.0002728165,0.6182965,0.0000683648,0.0002052944,0.0003673861,0.000009137164,0.001134937,0.001759044],"genre_scores_gemma":[0.3957422,0.000004857868,0.6039674,0.00009642614,0.00003035735,0.000008381874,0.00001143868,0.000003500313,0.0001354172],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9253941,"threshold_uncertainty_score":0.3591237,"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."}}