{"id":"W2132001515","doi":"10.3115/1626355.1626372","title":"Mixture-model adaptation for SMT","year":2007,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":253,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Machine translation; Granularity; Adaptation (eye); BLEU; Translation (biology); Domain adaptation; Log-linear model; Artificial intelligence; Baseline (sea); Language model; Natural language processing; Algorithm; Linear model; Machine learning; 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":[0.0003191394,0.00005457127,0.00004816077,0.00005915138,0.00004964243,0.0000587484,0.000374891,0.00004653563,0.000001579509],"category_scores_gemma":[0.00004606015,0.00004312814,0.0000270447,0.0001274506,0.000008451129,0.0003194184,0.00004947123,0.00004664067,0.000003274663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002041597,"about_ca_system_score_gemma":0.00002543984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007816922,"about_ca_topic_score_gemma":0.00002026939,"domain_scores_codex":[0.999491,0.000003126617,0.00009510128,0.0001585031,0.0001032277,0.0001490627],"domain_scores_gemma":[0.9996144,0.00005529132,0.00003290662,0.0001771494,0.00008826527,0.0000320094],"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":[0.000005860371,0.00001336693,0.000003783325,0.000009755881,0.000001970225,0.000001546958,0.0003970059,0.00004786933,0.005890529,0.7454311,0.002783799,0.2454135],"study_design_scores_gemma":[0.00008551745,0.00002680934,0.000006071923,0.000005461947,0.00000137773,0.000003410718,0.000009751882,0.6212881,0.1058144,0.2716692,0.0009962338,0.00009363269],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001505039,0.0002595308,0.996206,0.0005008159,0.00006211818,0.0001192525,3.725555e-7,0.0006527637,0.002048672],"genre_scores_gemma":[0.263548,6.502431e-7,0.7350555,0.0006083972,0.00002435954,0.000005435936,0.000001155313,0.000003243843,0.0007532641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6212403,"threshold_uncertainty_score":0.1758714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02364179146064855,"score_gpt":0.3049751683204618,"score_spread":0.2813333768598132,"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."}}