{"id":"W2142669279","doi":"10.3115/v1/w14-3363","title":"Linear Mixture Models for Robust Machine Translation","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Domain adaptation; Computer science; Machine translation; Leverage (statistics); Artificial intelligence; Adaptation (eye); Translation (biology); Machine learning; Domain (mathematical analysis); Repurposing; Robustness (evolution); Quality (philosophy); Linear model; Homogeneous; Mathematics","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":[0.0002058875,0.00007834741,0.00008093144,0.00004769612,0.00005908511,0.00006142318,0.0004387659,0.00006551738,0.000004120743],"category_scores_gemma":[0.00002110271,0.00005822132,0.0000405477,0.0001189028,0.000008870843,0.0004640068,0.0000327642,0.00007451416,0.000002456883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008039612,"about_ca_system_score_gemma":0.00001030013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001334307,"about_ca_topic_score_gemma":0.00001167281,"domain_scores_codex":[0.9994497,0.00001662932,0.0001004466,0.0002036073,0.0001039507,0.0001256984],"domain_scores_gemma":[0.9995721,0.0000599598,0.00003107804,0.0002402435,0.00006436658,0.0000322514],"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":[0.000008527701,0.00002547915,0.000004095438,0.0000447338,0.000005037686,4.651701e-7,0.0002786084,0.003713416,0.001642628,0.4073543,0.001506191,0.5854166],"study_design_scores_gemma":[0.0001125322,0.00003179503,5.070534e-7,0.000006817267,0.00000199482,0.000002237621,4.674243e-7,0.8721006,0.006950288,0.1191771,0.00153557,0.00008006693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001637086,0.0007304352,0.995032,0.001913911,0.00005836991,0.0001477453,0.000001516795,0.0007404763,0.001359144],"genre_scores_gemma":[0.1138698,0.00000227858,0.8852903,0.0004606638,0.00005833131,0.00001246124,0.000006401037,0.000006728977,0.0002930307],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8683872,"threshold_uncertainty_score":0.2374196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02622998605277226,"score_gpt":0.2692085829693952,"score_spread":0.2429785969166229,"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."}}