{"id":"W2909407853","doi":"10.22215/etd/2018-12972","title":"A Corpus-Based Investigation of Academic Vocabulary and Phrasal Verbs in Academic Spoken English","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"College of Pharmacy, University of Michigan; University of Warwick; Arts and Humanities Research Council; British Academy; University of Michigan","keywords":"Vocabulary; Noun; British National Corpus; Linguistics; Computer science; Corpus linguistics; Natural language processing; Verb; Word list; Artificial intelligence; Word (group theory); Part of speech","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":[0.001568535,0.0001310133,0.00020221,0.002924833,0.0009828607,0.001181753,0.0003555994,0.0003048169,0.001797466],"category_scores_gemma":[0.01017166,0.0001474763,0.0001092489,0.003476083,0.0009346536,0.001134094,0.001110875,0.000512149,0.0003020787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007112331,"about_ca_system_score_gemma":0.0009993807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005667664,"about_ca_topic_score_gemma":0.0169107,"domain_scores_codex":[0.9988958,0.0005134032,0.0001216648,0.0001920895,0.0002324704,0.00004456886],"domain_scores_gemma":[0.9878429,0.009212424,0.0009730077,0.0005432278,0.001239588,0.0001887746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0005388102,0.0009911322,0.2459611,0.002381121,0.00009981321,0.001602268,0.3353917,0.00126381,0.1009818,0.01240119,0.005275431,0.2931118],"study_design_scores_gemma":[0.00004713798,0.0004284587,0.8260676,0.0004188908,0.00008081114,0.002083547,0.1139361,0.002989462,0.01678284,0.001867107,0.03523122,0.00006676989],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9923387,0.0003646456,0.001931284,0.00008030755,0.00001012582,0.0001113225,0.0009496452,0.00001470004,0.004199137],"genre_scores_gemma":[0.9906887,0.0004785239,0.00544673,0.00003870176,0.00001336299,0.0003078409,0.001635459,0.00002172107,0.001369026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005667664,"threshold_uncertainty_score":0.01126933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02221661586677118,"score_gpt":0.336204979187352,"score_spread":0.3139883633205808,"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."}}