{"id":"W2736986829","doi":"10.18653/v1/w17-4704","title":"Modeling Target-Side Inflection in Neural Machine Translation","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nutrasource","funders":"European Commission","keywords":"Inflection; Computer science; Lemma (botany); Machine translation; Generalization; Natural language processing; Vocabulary; Artificial intelligence; Word (group theory); Czech; Simple (philosophy); Translation (biology); Byte; German; Transfer-based machine translation; Example-based machine translation; Speech recognition; Linguistics; 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":[0.002018044,0.000773057,0.0006888427,0.0007844424,0.0006081829,0.001522264,0.0009474782,0.001368503,0.003523234],"category_scores_gemma":[0.01297659,0.0005410719,0.0006425983,0.001289687,0.0005630355,0.003141304,0.0009038183,0.001753873,0.00225885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006825142,"about_ca_system_score_gemma":0.0009304078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004078183,"about_ca_topic_score_gemma":0.006748454,"domain_scores_codex":[0.9991813,0.0004310035,0.00006260694,0.0001889023,0.0000860911,0.00004998286],"domain_scores_gemma":[0.9957847,0.003080731,0.0001783302,0.0004864184,0.0004123611,0.00005749303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007244125,0.0001495792,0.004251563,0.0006861772,0.0002392414,0.0004992441,0.0004471584,0.5279508,0.01771432,0.0470742,0.01131057,0.3889528],"study_design_scores_gemma":[0.0000202824,0.0000387409,0.0005177097,0.0000230259,0.00002315497,0.00007816777,0.00003276316,0.9488333,0.004519426,0.04421968,0.001678825,0.00001484337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1153345,0.002741104,0.8690375,0.001308208,0.0004312141,0.00007741085,0.0007841741,0.002909311,0.007376595],"genre_scores_gemma":[0.8450733,0.001140361,0.1438775,0.0002692751,0.0002979405,0.0001611544,0.001629672,0.0008388842,0.006711785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004078183,"threshold_uncertainty_score":0.0117864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03841417308779047,"score_gpt":0.3189246943813484,"score_spread":0.2805105212935579,"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."}}