{"id":"W2001023236","doi":"10.1145/1236181.1236184","title":"Statistical query translation models for cross-language information retrieval","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Cross-language information retrieval; Natural language processing; Query expansion; Artificial intelligence; Machine translation; Query language; RDF query language; Translation (biology); Dependency (UML); Query optimization; Context (archaeology); Information retrieval; Web query classification; Web search query; Search engine","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","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005105416,0.0003217124,0.0002493483,0.0006433399,0.0005811251,0.001512895,0.0008725502,0.0002604815,0.00003115084],"category_scores_gemma":[0.0001444182,0.0003120543,0.000121749,0.0007839467,0.00008449572,0.01842866,0.00001755685,0.0003977772,0.0000398557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001919868,"about_ca_system_score_gemma":0.0002036884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000788875,"about_ca_topic_score_gemma":0.00001484149,"domain_scores_codex":[0.9976605,0.00004766566,0.0009193224,0.0002727475,0.0006336929,0.0004660343],"domain_scores_gemma":[0.998332,0.000155142,0.0004115057,0.0006220259,0.0003745766,0.0001047714],"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":[0.0001288922,0.00005608483,0.000002890393,0.0003234555,0.00001075369,0.00000302338,0.01013303,0.003244778,0.0003827674,0.007259111,0.0001157085,0.9783395],"study_design_scores_gemma":[0.003546647,0.0003615831,0.0001817345,0.000401652,0.00008405549,0.0001493169,0.003851819,0.8500168,0.06670504,0.07057296,0.00256038,0.001567957],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008244744,0.0004000313,0.9938797,0.0007069206,0.0001736563,0.000686216,0.0001788215,0.00134691,0.001803231],"genre_scores_gemma":[0.5235724,0.000002592331,0.4754806,0.0004600415,0.0000459971,0.00006370942,0.0003110505,0.00001384807,0.00004969025],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9767715,"threshold_uncertainty_score":0.9999332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01185437753511291,"score_gpt":0.2911378651152146,"score_spread":0.2792834875801017,"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."}}