{"id":"W4303437372","doi":"10.7202/1092197ar","title":"Quantitative questions on big data in translation studies","year":2022,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Translation Studies and Practices","field":"Arts and Humanities","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Variety (cybernetics); Data science; Big data; Field (mathematics); Natural language processing; Corpus linguistics; Translation (biology); Translation studies; Sentiment analysis; Artificial intelligence; Machine translation; Linguistics; Data mining; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.120001,0.001104851,0.001140376,0.008702404,0.007917046,0.02186728,0.002582635,0.004759957,0.008855387],"category_scores_gemma":[0.2805344,0.000869138,0.00116387,0.02162039,0.03241958,0.04451819,0.009210375,0.006925062,0.001084925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007889498,"about_ca_system_score_gemma":0.007619003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0024365,"about_ca_topic_score_gemma":0.002191809,"domain_scores_codex":[0.8218067,0.1515719,0.005398994,0.005490121,0.01417066,0.00156162],"domain_scores_gemma":[0.5421458,0.4013426,0.0162111,0.02015891,0.01775355,0.002388007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007415372,0.00008000011,0.005917835,0.001399416,0.00008276825,0.0001578305,0.03748737,0.0008160645,0.0003459455,0.9073314,0.008714817,0.03759234],"study_design_scores_gemma":[0.00003327773,0.00009236913,0.005069418,0.003154036,0.00004143479,0.000214038,0.05856029,0.00272813,0.0006038822,0.8546156,0.07481649,0.00007098274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.1113169,0.02326957,0.3342236,0.3488403,0.004808365,0.002120821,0.004608247,0.0003032358,0.170509],"genre_scores_gemma":[0.8135198,0.01031566,0.1303325,0.02708231,0.004482449,0.005747615,0.001441983,0.000424426,0.006653141],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.120001,"threshold_uncertainty_score":0.6346337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4622568889228398,"score_gpt":0.3908865321108239,"score_spread":0.07137035681201592,"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."}}