{"id":"W3004276871","doi":"10.7202/1073635ar","title":"Comparing across languages in corpus and discourse analysis: some issues and approaches","year":2020,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rhetorical question; Salient; Computer science; Linguistics; Corpus linguistics; Context (archaeology); Intersection (aeronautics); Natural language processing; Set (abstract data type); Artificial intelligence; History; Geography","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":[0.2297764,0.001763179,0.003400959,0.03467352,0.01665674,0.04248948,0.01046678,0.007482234,0.006118108],"category_scores_gemma":[0.3021448,0.002296512,0.001852189,0.03764921,0.04881605,0.04821717,0.02725643,0.00919554,0.001065913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01432875,"about_ca_system_score_gemma":0.01069497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01282558,"about_ca_topic_score_gemma":0.01374807,"domain_scores_codex":[0.5838507,0.3836271,0.009649226,0.008624166,0.01270896,0.0015398],"domain_scores_gemma":[0.4951438,0.4357537,0.009526234,0.03423568,0.02312734,0.002213178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009246698,0.0001301156,0.004868297,0.001717343,0.0003104434,0.0003419677,0.1245923,0.0009682964,0.0006034201,0.7659513,0.004653258,0.09577078],"study_design_scores_gemma":[0.00006841632,0.0001109735,0.004341053,0.00497746,0.0001199134,0.0006473748,0.1183668,0.005796852,0.001663583,0.7582913,0.1054409,0.0001753189],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03720898,0.05013681,0.7428432,0.08736908,0.002048999,0.002041981,0.001036503,0.0004927829,0.07682166],"genre_scores_gemma":[0.3533777,0.008978989,0.6173607,0.004587331,0.001386382,0.00799217,0.0007838454,0.0008088113,0.00472418],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2297764,"threshold_uncertainty_score":0.9498228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.119692252219888,"score_gpt":0.321223015178789,"score_spread":0.201530762958901,"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."}}