{"id":"W3031229455","doi":"","title":"SEDAR: a Large Scale French-English Financial Domain Parallel Corpus","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Machine translation; Computer science; Domain (mathematical analysis); Preprocessor; Natural language processing; Sentence; Translation (biology); Artificial intelligence; Scale (ratio); Speech recognition; Chemistry","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006982129,0.0001396146,0.0001609846,0.00005459235,0.0001599816,0.0002300148,0.0003954991,0.0000986356,0.00004327601],"category_scores_gemma":[0.0003135253,0.0001201593,0.00004441828,0.000319001,0.00003141639,0.0003293082,0.0002193607,0.0001815652,0.000009422372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002765691,"about_ca_system_score_gemma":0.00004737978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004955863,"about_ca_topic_score_gemma":0.00004828307,"domain_scores_codex":[0.9985406,0.0001449224,0.0001841933,0.000394936,0.0004871407,0.0002481552],"domain_scores_gemma":[0.999359,0.00004198803,0.0001066191,0.0002424413,0.0001307494,0.0001191716],"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":[0.00007444064,0.0001376878,0.002827037,0.0002317381,0.00003180453,0.000105771,0.439784,0.00008844609,0.007667312,0.01194092,0.0100771,0.5270337],"study_design_scores_gemma":[0.007512795,0.001164893,0.01221303,0.0004062494,0.0001749114,0.00008084433,0.008321859,0.7896857,0.008396556,0.07013818,0.09958011,0.002324916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.675015,0.01966318,0.3004294,0.002112737,0.0001463969,0.0004778114,0.00001533541,0.0008217991,0.001318256],"genre_scores_gemma":[0.8065178,0.00002357751,0.1912846,0.001624329,0.0004207074,0.00003466854,0.00002211671,0.00001179197,0.00006036493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7895972,"threshold_uncertainty_score":0.4899954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01198234994470673,"score_gpt":0.2627608228998279,"score_spread":0.2507784729551212,"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."}}