{"id":"W2587623425","doi":"10.5539/mas.v11n4p55","title":"An Investigation into Methodology and Metrics Employed to Evaluate the (Speech-to-Speech) Way in Translation Systems","year":2017,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Speech translation; Computer science; Speech recognition; Machine translation; Natural language processing; Translation (biology); Artificial intelligence; Sentence; Speech synthesis; Example-based machine translation; Speech processing; Speech corpus; Evaluation of machine translation; Machine translation software usability","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04069755,0.001661904,0.001490423,0.008279276,0.001210429,0.004685668,0.001588747,0.002572207,0.001015456],"category_scores_gemma":[0.1253213,0.0004629788,0.001085254,0.006718797,0.002093341,0.005212277,0.002533408,0.001559903,0.0006411145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002341201,"about_ca_system_score_gemma":0.001722654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002461466,"about_ca_topic_score_gemma":0.002434456,"domain_scores_codex":[0.9417955,0.03302439,0.008438963,0.003924422,0.01219522,0.0006216166],"domain_scores_gemma":[0.8723701,0.07767839,0.01361155,0.009707561,0.02560622,0.001026224],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001139431,0.000643157,0.09280545,0.003980069,0.001617298,0.0002960458,0.004711875,0.0965036,0.04640177,0.03230673,0.003182656,0.7164119],"study_design_scores_gemma":[0.0002053534,0.01092623,0.1188188,0.00129494,0.0008528839,0.002661576,0.005501712,0.6316792,0.1385003,0.05265234,0.03603765,0.0008690074],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.195646,0.009346415,0.7816976,0.0007243173,0.0003689899,0.00103487,0.001672912,0.002474644,0.007034257],"genre_scores_gemma":[0.5017381,0.00141782,0.4928108,0.0001442206,0.0001018166,0.0007176166,0.001705682,0.0003518656,0.001012014],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9593024,"threshold_uncertainty_score":0.2152318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1018019349674242,"score_gpt":0.3742426121673111,"score_spread":0.2724406771998869,"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."}}