{"id":"W2143564602","doi":"10.3115/1220175.1220271","title":"An end-to-end discriminative approach to machine translation","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":265,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Microsoft Research","keywords":"Discriminative model; Computer science; Artificial intelligence; Machine translation; Phrase; Heuristic; Feature (linguistics); Machine learning; Translation (biology); Process (computing); Decoding methods; Perceptron; Natural language processing; Pattern recognition (psychology); Artificial neural network; Algorithm","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0001917175,0.0001237996,0.0001049571,0.0001674421,0.0000770994,0.0001834594,0.0007362315,0.00004281207,0.00001394801],"category_scores_gemma":[0.000009215593,0.00009515673,0.00002709582,0.0004942177,0.00001549921,0.0006549979,0.00007239838,0.00009493822,0.0000133978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003463015,"about_ca_system_score_gemma":0.00001668149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004959152,"about_ca_topic_score_gemma":0.0001127597,"domain_scores_codex":[0.9989707,0.00004404653,0.0001418201,0.0003953145,0.0002496518,0.0001984246],"domain_scores_gemma":[0.999449,0.00001985789,0.00002717049,0.000358087,0.00005677923,0.00008917431],"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":[0.000009359938,0.0002195623,0.00006638086,0.00001574408,0.000003498649,0.000004748443,0.003138875,0.0001290268,0.02144773,0.3275932,0.0009988871,0.646373],"study_design_scores_gemma":[0.000559366,0.0006903257,0.00343492,0.00005054036,0.00002246627,0.00004731104,0.0001853271,0.4397437,0.3782307,0.170882,0.004723857,0.001429447],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008634342,0.0001982942,0.9753556,0.001505734,0.00003463022,0.0002407915,0.000003972821,0.0007527042,0.02104485],"genre_scores_gemma":[0.4885909,1.095066e-7,0.5108249,0.0003060194,0.00002657495,0.00001473618,0.00001027602,0.00000491696,0.0002215971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6449435,"threshold_uncertainty_score":0.3880379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01802462325358629,"score_gpt":0.2828060711697341,"score_spread":0.2647814479161478,"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."}}