{"id":"W2738790619","doi":"10.7202/1040469ar","title":"Genre and Register in Comparable Corpora: An English/Spanish Contrastive Analysis","year":2017,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Junta de Castilla y León","keywords":"Representativeness heuristic; Computer science; Register (sociolinguistics); Linguistics; Natural language processing; Corpus linguistics; Selection (genetic algorithm); Artificial intelligence; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.009229497,0.0004530667,0.0005318416,0.01014608,0.001607431,0.00360185,0.0006698179,0.0005462176,0.004521629],"category_scores_gemma":[0.04449507,0.0002707044,0.0006119282,0.01106217,0.00176496,0.002134201,0.002327493,0.001127589,0.0006772887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001562489,"about_ca_system_score_gemma":0.0006934211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005742076,"about_ca_topic_score_gemma":0.005945335,"domain_scores_codex":[0.9929929,0.004033349,0.0007336551,0.0009487509,0.001034101,0.0002572686],"domain_scores_gemma":[0.962141,0.02842045,0.001965416,0.002293785,0.004746465,0.0004328488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.004792975,0.0009379698,0.1946629,0.004808106,0.0009995393,0.005649511,0.217818,0.001604488,0.04877174,0.06399195,0.02588293,0.4300801],"study_design_scores_gemma":[0.0005260454,0.0008437979,0.5930588,0.001406553,0.001275772,0.003254765,0.09691714,0.0104912,0.0142467,0.01737645,0.2603865,0.0002162047],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8987891,0.004487025,0.03454814,0.0008432554,0.0002567613,0.0007824561,0.006089624,0.0003447566,0.05385889],"genre_scores_gemma":[0.9657342,0.0005628741,0.0239496,0.0001153344,0.0001366603,0.0006817249,0.005901588,0.0003183643,0.002599578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01014608,"threshold_uncertainty_score":0.04881084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0464162821350621,"score_gpt":0.3024912447061955,"score_spread":0.2560749625711334,"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."}}