{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004101975,0.00008429936,0.000102811,0.000117189,0.00004189876,0.0001320749,0.0003166136,0.00006970866,0.000002978272],"category_scores_gemma":[0.0001515426,0.00007353764,0.00001906188,0.0001493122,0.00002432986,0.0009435071,0.0001322249,0.0001040026,0.000003364304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002292284,"about_ca_system_score_gemma":0.00002810795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003120272,"about_ca_topic_score_gemma":0.00001249669,"domain_scores_codex":[0.9993724,0.00002604012,0.0001560315,0.0001521805,0.0001223927,0.0001709759],"domain_scores_gemma":[0.9995355,0.00008469438,0.00006233071,0.0002260907,0.00005237874,0.00003901591],"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":[0.0000140002,0.00002194284,0.0000647945,0.00009821318,0.000003200049,0.000001363558,0.01017388,0.0001331067,0.006119803,0.1138893,0.0006173421,0.8688631],"study_design_scores_gemma":[0.0003035149,0.00004124373,0.00001716767,0.00002811642,0.000002071802,0.000005490038,0.00007640878,0.8505611,0.006763148,0.1405981,0.001472677,0.0001308832],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06116097,0.0001457327,0.9364147,0.0003799109,0.00003682395,0.0001819748,0.000001612371,0.000265732,0.001412581],"genre_scores_gemma":[0.543434,0.000001663826,0.4559841,0.0004405228,0.00002124683,0.00001517181,0.000003071376,0.000004011875,0.00009619496],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8687322,"threshold_uncertainty_score":0.2998778,"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."}}