{"id":"W2166001215","doi":"","title":"Going Beyond Word Cooccurrences in Global Lexical Selection for Statistical Machine Translation using a Multilayer Perceptron","year":2011,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Phrase; Artificial intelligence; Natural language processing; Machine translation; Word (group theory); Sentence; Perceptron; Selection (genetic algorithm); Speech recognition; Context (archaeology); Translation (biology); Example-based machine translation; Artificial neural network; Linguistics","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":[0.002414713,0.000886542,0.001171052,0.0008141723,0.0005410516,0.001097955,0.0009384566,0.0008300403,0.00281477],"category_scores_gemma":[0.004602174,0.0005487553,0.0007866679,0.001297607,0.0007461413,0.002951903,0.001266911,0.001547735,0.001634628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005041923,"about_ca_system_score_gemma":0.000964533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003116061,"about_ca_topic_score_gemma":0.007131122,"domain_scores_codex":[0.9988548,0.0004571888,0.0001083667,0.0002569091,0.0002171523,0.0001056302],"domain_scores_gemma":[0.9979163,0.001066634,0.0002000275,0.0003801524,0.0003582403,0.00007871283],"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":[0.0007229701,0.0002546079,0.005392844,0.0003793938,0.0004033892,0.0005307927,0.000369311,0.2709287,0.08163612,0.0155458,0.003962205,0.6198739],"study_design_scores_gemma":[0.0000301494,0.0001564695,0.001218099,0.00002363291,0.0000925325,0.0001237265,0.00003487991,0.9605815,0.01667461,0.01950551,0.001521879,0.00003705413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04707476,0.0004028497,0.9492538,0.0002527999,0.00005009634,0.00004057927,0.00009830656,0.001608325,0.001218503],"genre_scores_gemma":[0.7348337,0.0004684242,0.258405,0.0002371961,0.0001242468,0.0001305981,0.0004342915,0.0003439354,0.00502277],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003116061,"threshold_uncertainty_score":0.01277041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05879728227907942,"score_gpt":0.3446044523753533,"score_spread":0.2858071700962738,"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."}}