{"id":"W1849783837","doi":"10.3968/5182","title":"Analyzing Collocation Errors in EFL Chinese Learners’ Writings Based on Corpus","year":2014,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Collocation (remote sensing); Computer science; Natural language processing; Linguistics; Process (computing); Artificial intelligence; Chinese as a foreign language; Foreign language; English as a foreign language; Programming language; Philosophy","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007810179,0.00007441003,0.0001088883,0.0003218386,0.0001772404,0.00002927776,0.0001882264,0.00005556367,0.007132194],"category_scores_gemma":[0.0001358864,0.00007384758,0.00003336005,0.001242348,0.0002132988,0.0001114296,0.00001005987,0.0001245317,0.0000788644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001274761,"about_ca_system_score_gemma":0.0001785847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002719257,"about_ca_topic_score_gemma":0.000002652616,"domain_scores_codex":[0.9990566,0.0001334455,0.0001883366,0.0002481841,0.0001914179,0.0001819582],"domain_scores_gemma":[0.9994371,0.00009751764,0.0001683312,0.0001415995,0.0001016539,0.00005381091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001468125,0.001323269,0.2599761,0.00005843007,0.00001229458,0.000001767759,0.06272538,0.0006684636,0.02986805,0.5753931,0.002887587,0.06693864],"study_design_scores_gemma":[0.0003065272,0.00005682118,0.9919336,0.00002074207,0.000003162086,4.231111e-7,0.002817325,0.0002450139,0.00009120564,0.0001596556,0.00426869,0.00009677142],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.788328,0.00005089555,0.00006668482,0.0005735885,0.0007182986,0.00007945012,5.086617e-7,0.00002488008,0.2101577],"genre_scores_gemma":[0.9931556,1.758134e-7,0.0001295232,0.003053104,0.0002177871,0.00001897836,0.00000797132,0.000007186001,0.003409652],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7319575,"threshold_uncertainty_score":0.9937754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01438131181450408,"score_gpt":0.348228203049243,"score_spread":0.3338468912347389,"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."}}