{"id":"W4230939024","doi":"10.22215/etd/2015-10720","title":"Enhancing Machine Translation for English-Japanese Using Syntactic Pattern Recognition Methods","year":2015,"lang":"en","type":"dissertation","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Machine translation; Sentence; Natural language processing; Artificial intelligence; String (physics); Set (abstract data type); Transfer-based machine translation; Translation (biology); Example-based machine translation; Matching (statistics); Representation (politics); String searching algorithm; Speech recognition; Pattern matching; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001196643,0.0009139081,0.0006313533,0.0008230433,0.0007132388,0.001368776,0.0005000932,0.000591923,0.005385929],"category_scores_gemma":[0.003059607,0.0002817014,0.0008546216,0.001185522,0.0003731231,0.001931055,0.0007222163,0.0009241611,0.003835395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003464222,"about_ca_system_score_gemma":0.0007920842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001108555,"about_ca_topic_score_gemma":0.002317152,"domain_scores_codex":[0.9991773,0.0002972436,0.00008388884,0.0001678523,0.0002118989,0.00006179602],"domain_scores_gemma":[0.9987381,0.0005504325,0.00009598944,0.0001960311,0.0003975644,0.0000219502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001723521,0.000278255,0.001374342,0.0009968202,0.0001008398,0.0004224482,0.0009122802,0.006944569,0.157221,0.01844078,0.008273937,0.8048624],"study_design_scores_gemma":[0.0001978826,0.0009263203,0.007002513,0.0002306162,0.0006343818,0.002150342,0.001355937,0.3339773,0.4635808,0.04411842,0.1456375,0.0001880652],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0612765,0.001160921,0.9160062,0.0008519984,0.0003691885,0.0002858565,0.0003221679,0.005121484,0.01460579],"genre_scores_gemma":[0.1892514,0.001358763,0.796595,0.0003158768,0.0001707227,0.0001997983,0.001116331,0.0006587759,0.01033326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005385929,"threshold_uncertainty_score":0.01801777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05884144728236558,"score_gpt":0.3947219384824856,"score_spread":0.33588049120012,"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."}}