{"id":"W3131063663","doi":"","title":"On the use of linguistic similarities to improve Neural Machine Translation for African Languages","year":2021,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Machine translation; Linguistics; Computer science; Translation (biology); Natural language processing; Artificial intelligence; Biology; Philosophy","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":[0.002241667,0.0006042995,0.000826965,0.001506097,0.0009837628,0.001236464,0.0009134076,0.001135656,0.005661323],"category_scores_gemma":[0.01265851,0.0002623544,0.0004940296,0.001823858,0.0005903373,0.002870405,0.001725439,0.001026494,0.001557321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004547108,"about_ca_system_score_gemma":0.0007283519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003035473,"about_ca_topic_score_gemma":0.006887149,"domain_scores_codex":[0.9990138,0.0004774022,0.00008147166,0.0001940639,0.0001534266,0.0000798781],"domain_scores_gemma":[0.9949456,0.003282798,0.0002637951,0.0005649534,0.0008467462,0.00009616121],"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":[0.001016183,0.0003190825,0.00388861,0.0003602306,0.0002030021,0.0002624758,0.0004203674,0.07345454,0.02124685,0.01736597,0.00783598,0.8736268],"study_design_scores_gemma":[0.0001731506,0.0004246989,0.003752842,0.0001024888,0.0002331419,0.0002560047,0.0004256783,0.9241466,0.02376878,0.03890961,0.007763088,0.0000438984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5561962,0.006985239,0.3975106,0.003421955,0.0008842684,0.0002474743,0.0007883792,0.003933308,0.03003263],"genre_scores_gemma":[0.8482271,0.001085442,0.1422597,0.0004347415,0.0003047169,0.00008180182,0.0009137048,0.0003888426,0.006304059],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005661323,"threshold_uncertainty_score":0.01893896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0299395203253814,"score_gpt":0.2667732652375862,"score_spread":0.2368337449122048,"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."}}