{"id":"W161681728","doi":"","title":"Using context-dependent interpolation to combine statistical language and translation models for interactive machine translation","year":2000,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Trigram; Computer science; Machine translation; Natural language processing; Translation (biology); Artificial intelligence; Context (archaeology); Example-based machine translation; Interpolation (computer graphics); Machine translation software usability; Language model; Transfer-based machine translation; Evaluation of machine translation; Machine learning","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":[0.0001883126,0.0001227138,0.0001472369,0.0001084147,0.00007231037,0.0001418893,0.0001703213,0.00005383941,0.00005421042],"category_scores_gemma":[0.0000144997,0.0001087548,0.00002968044,0.000119156,0.00001614386,0.0009556147,0.00001997608,0.00009420424,0.00000196829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000378832,"about_ca_system_score_gemma":0.00001527324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002848479,"about_ca_topic_score_gemma":0.0001203692,"domain_scores_codex":[0.9991361,0.00004365399,0.0002149604,0.0003038968,0.0001526914,0.0001486472],"domain_scores_gemma":[0.999532,0.0001618029,0.00003516846,0.000150254,0.00005375452,0.00006703057],"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":[0.00011439,0.00002950104,0.000004024228,0.00001770888,0.00001171956,0.000001791178,0.004631051,0.0002939424,0.006414162,0.01593747,0.00001445132,0.9725298],"study_design_scores_gemma":[0.0004567447,0.0001205361,0.000006958559,0.00003370305,0.00001270518,0.00001199259,0.00006978839,0.9677077,0.005507099,0.02587385,0.00005742467,0.0001414769],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005010427,0.001009362,0.9923375,0.0004925469,0.00003635927,0.0005353314,0.0000321189,0.0002466029,0.0002997717],"genre_scores_gemma":[0.5252412,0.000002422901,0.4745187,0.0001664376,0.000009668923,0.00001053435,0.00001454681,0.000006242586,0.00003023661],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9723883,"threshold_uncertainty_score":0.4434892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03654301589907547,"score_gpt":0.3358021189952543,"score_spread":0.2992591030961788,"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."}}