{"id":"W2807690984","doi":"10.1515/cllt-2017-0031","title":"Dependency profiles in the large-scale analysis of discourse connectives","year":2018,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Brock University","funders":"Turun Yliopisto","keywords":"Dependency (UML); Computer science; Syntax; Natural language processing; Scope (computer science); Artificial intelligence; Linguistics; Cluster analysis; Focus (optics); Annotation","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.002752697,0.0003076451,0.0003888071,0.005436469,0.001118649,0.001460055,0.0005216671,0.0004580973,0.001690256],"category_scores_gemma":[0.02017612,0.000311382,0.0003720756,0.005369746,0.0008565122,0.002343908,0.001586274,0.0007139984,0.0003915187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006949287,"about_ca_system_score_gemma":0.0006118932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002616636,"about_ca_topic_score_gemma":0.00297735,"domain_scores_codex":[0.9971225,0.001599053,0.0001958342,0.0005567312,0.0004218007,0.0001040025],"domain_scores_gemma":[0.9806595,0.01579552,0.001267169,0.0009758236,0.001008686,0.0002933796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001958935,0.0006284557,0.3414882,0.001604617,0.0005382732,0.002589856,0.02976373,0.03659714,0.07716006,0.05978592,0.005376163,0.4425086],"study_design_scores_gemma":[0.00006643283,0.0002854382,0.4457504,0.0002856509,0.000279409,0.001860971,0.01337302,0.4016338,0.04212883,0.07123075,0.02290628,0.0001988892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8931143,0.0003840319,0.1012319,0.0001161829,0.00001633798,0.0001347994,0.001917422,0.0002895597,0.002795661],"genre_scores_gemma":[0.9650618,0.0000842736,0.03331181,0.00001110342,0.000008862354,0.0001285581,0.001068583,0.00004661574,0.0002782821],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005436469,"threshold_uncertainty_score":0.01455778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00909766402107549,"score_gpt":0.2919299757573142,"score_spread":0.2828323117362387,"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."}}