{"id":"W2168801328","doi":"10.1162/089120103322711587","title":"Embedding Web-Based Statistical Translation Models in Cross-Language Information Retrieval","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Cross-language information retrieval; Machine translation; Natural language processing; Information retrieval; Artificial intelligence; Process (computing); Translation (biology); Machine translation software usability; Language model; Embedding; Example-based machine translation; Programming language","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":[0.0005225721,0.0001539222,0.0001512467,0.0002191649,0.0001083271,0.0003302728,0.0003347083,0.0001072752,0.00001110545],"category_scores_gemma":[0.002453764,0.0001640194,0.00003483359,0.0004855964,0.00005670328,0.0004436964,0.00003110208,0.0002552752,0.00001344085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001213119,"about_ca_system_score_gemma":0.0003620649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007054949,"about_ca_topic_score_gemma":0.000001702224,"domain_scores_codex":[0.9984801,0.00009080976,0.0004694044,0.0002339619,0.0004842656,0.0002414387],"domain_scores_gemma":[0.998595,0.0005175382,0.0001366653,0.000189264,0.0004883151,0.0000732082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001755239,0.00003593525,0.0001187246,0.00004691873,0.000002969734,0.00002051147,0.0005240428,0.4167165,0.0000264962,0.5791559,0.00006382804,0.003270628],"study_design_scores_gemma":[0.0004634931,0.00002294461,0.00007013683,0.00003058062,0.000002655476,0.000004228568,0.000008282535,0.7859287,0.0003584665,0.212554,0.0004016501,0.0001548898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001831124,0.0002682963,0.9952231,0.0000373578,0.0003121331,0.0001602644,0.00003148464,0.0003290417,0.001807213],"genre_scores_gemma":[0.5022816,5.901915e-7,0.4974518,0.000151307,0.00002989678,0.000002706214,0.00007354189,0.000005278765,0.000003313211],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5004505,"threshold_uncertainty_score":0.6688515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01959166820152231,"score_gpt":0.3257819259314265,"score_spread":0.3061902577299042,"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."}}