{"id":"W2311921240","doi":"10.18653/v1/p16-1160","title":"A Character-level Decoder without Explicit Segmentation for Neural Machine Translation","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":182,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Samsung; Canada Research Chairs; Canadian Institute for Advanced Research; Nvidia","keywords":"Machine translation; Computer science; Character (mathematics); Phrase; Segmentation; Encoder; Artificial intelligence; Speech recognition; Natural language processing; Translation (biology); Sequence (biology); Language model; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002780133,0.0003147468,0.0002851578,0.000189475,0.00009133067,0.0003213777,0.001029605,0.0002507148,0.00002012214],"category_scores_gemma":[0.0000264049,0.0002258492,0.0001424842,0.00008951698,0.00001610117,0.0007070253,0.0003641922,0.0002656989,0.000006532766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008508483,"about_ca_system_score_gemma":0.00007597241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003382858,"about_ca_topic_score_gemma":0.00002828337,"domain_scores_codex":[0.9983044,0.00005028631,0.0003704081,0.0007152538,0.0002799988,0.0002796759],"domain_scores_gemma":[0.9987729,0.00009789871,0.0002817248,0.0006077587,0.0001715374,0.00006813164],"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":[0.0000399165,0.00004243721,0.0001947044,0.0002256364,0.00003401061,0.000002279913,0.0007406023,0.000006149227,0.02055314,0.008006885,0.0003554332,0.9697988],"study_design_scores_gemma":[0.001275345,0.0001296726,0.0003346493,0.0003974978,0.0000534376,0.00002844743,0.00000790998,0.674504,0.1500333,0.1714528,0.0006096716,0.001173317],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001013914,0.001155523,0.9918047,0.003103196,0.0004710811,0.001106477,0.00007921699,0.00109686,0.0001690849],"genre_scores_gemma":[0.2599961,0.00001204309,0.7383282,0.0005280204,0.0001489632,0.0003562552,0.0001076021,0.00002621548,0.0004965406],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9686255,"threshold_uncertainty_score":0.9209862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06178756432298701,"score_gpt":0.3361341854023093,"score_spread":0.2743466210793223,"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."}}