{"id":"W3185386956","doi":"","title":"Coarse \"split and lump\" bilingual language models for richer source information in SMT.","year":2014,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Machine translation; Natural language processing; Language model; Word (group theory); Artificial intelligence; Phrase; Sentence; Speech recognition; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001947988,0.001574789,0.0008261667,0.001088618,0.0005788463,0.001175083,0.001210006,0.001083584,0.006383952],"category_scores_gemma":[0.005834064,0.0005915542,0.001076579,0.0009479541,0.0006015481,0.003002864,0.002043454,0.002315061,0.004733335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008081711,"about_ca_system_score_gemma":0.001191225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004568937,"about_ca_topic_score_gemma":0.01641494,"domain_scores_codex":[0.9988776,0.0005994936,0.00005010395,0.000293447,0.0001148318,0.00006456905],"domain_scores_gemma":[0.9980084,0.001053889,0.00008391426,0.0005853706,0.0001696405,0.00009880362],"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":[0.001547348,0.0005148989,0.005927668,0.0005451418,0.000539633,0.0002979023,0.0006182258,0.4439097,0.03137499,0.02287948,0.02394371,0.4679014],"study_design_scores_gemma":[0.00007360835,0.0001247936,0.0008471073,0.00002734734,0.00005187951,0.00008553176,0.00007289022,0.9654142,0.006200868,0.02261725,0.004452356,0.00003217698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09783728,0.001195032,0.8754168,0.0007914499,0.0001999613,0.0002043155,0.002099858,0.01594975,0.006305492],"genre_scores_gemma":[0.6659897,0.0002758837,0.31986,0.000630863,0.0001121863,0.0003885519,0.006078019,0.001488683,0.005176059],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006383952,"threshold_uncertainty_score":0.02135646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009044135863205661,"score_gpt":0.2524401928076209,"score_spread":0.2433960569444153,"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."}}