{"id":"W3185884227","doi":"10.17533/udea.mut.v14n2a10","title":"Cadlaws – An English–French Parallel Corpus of Legally Equivalent Documents","year":2021,"lang":"en","type":"article","venue":"Mutatis Mutandis Revista Latinoamericana de Traducción","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Machine translation; Parallel corpora; Corpus linguistics; Artificial intelligence; Meaning (existential); Linguistics; Translation (biology); Baseline (sea); Psychology; Political science; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00190188,0.0008141571,0.0005720892,0.009271092,0.004381918,0.002095446,0.001231239,0.0008089407,0.01621483],"category_scores_gemma":[0.009237751,0.0003532742,0.000463956,0.007605761,0.001910373,0.001054408,0.001280707,0.001093461,0.00324166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008959057,"about_ca_system_score_gemma":0.01717998,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.6728865,"about_ca_topic_score_gemma":0.6848592,"domain_scores_codex":[0.9975839,0.0005165172,0.0002011979,0.0005286022,0.0009035309,0.0002661974],"domain_scores_gemma":[0.9939658,0.001683101,0.0002666329,0.0005542261,0.003216192,0.0003140721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001045997,0.0006304035,0.0115532,0.003716121,0.0001692532,0.003790081,0.01086946,0.005405624,0.02018685,0.04273551,0.511974,0.3879236],"study_design_scores_gemma":[0.0001945127,0.00007279021,0.03159108,0.0003996616,0.00006753658,0.001129221,0.003548669,0.003459524,0.007699002,0.00224281,0.9494812,0.0001140243],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.3182814,0.007157319,0.0327636,0.00296727,0.001321021,0.003341808,0.5226185,0.0056562,0.1058929],"genre_scores_gemma":[0.3095344,0.001873143,0.05867965,0.0005246812,0.0002146749,0.002071767,0.5967005,0.001135114,0.02926599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6728865,"threshold_uncertainty_score":0.6580799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01316222300862668,"score_gpt":0.2824966669699034,"score_spread":0.2693344439612768,"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."}}