{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004501686,0.000249778,0.000837856,0.0001880763,0.0004220621,0.0007591769,0.0001869988,0.00002562204,0.000140366],"category_scores_gemma":[0.00007609773,0.0001772323,0.0002329437,0.000181779,0.0009466934,0.0007130428,0.00009653514,0.0003052172,0.000003411089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000137572,"about_ca_system_score_gemma":0.000007784088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002881163,"about_ca_topic_score_gemma":0.003147285,"domain_scores_codex":[0.9985804,0.0001538141,0.0003780406,0.0003047379,0.0002421662,0.0003408354],"domain_scores_gemma":[0.9994561,0.00005926259,0.0001579475,0.0001255863,0.00004004741,0.0001610201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001368073,0.000339813,0.1883563,0.0002890687,0.03410787,0.0006945119,0.56611,0.00110658,0.0001537815,0.1213883,0.0006383769,0.08667847],"study_design_scores_gemma":[0.002936438,0.0004859848,0.1818997,0.0001777584,0.03929393,0.0002278622,0.7256879,0.004672419,0.0003491499,0.01396593,0.02823192,0.002070977],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7835545,0.2137635,0.00007318168,0.001754567,0.00005173392,0.00006160857,0.00001736074,0.00002568569,0.0006978316],"genre_scores_gemma":[0.9887869,0.009738864,0.000230768,0.0001947733,0.0005590973,0.0000066848,0.000005941963,0.00002001442,0.0004569613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2052324,"threshold_uncertainty_score":0.732076,"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."}}