{"id":"W2251281667","doi":"10.3115/v1/p14-2138","title":"Does the Phonology of L1 Show Up in L2 Texts?","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Bigram; Phonology; Computer science; Character (mathematics); Discriminative model; Natural language processing; Artificial intelligence; Task (project management); Word (group theory); Linguistics; Identification (biology); Language model; Mathematics; Trigram; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0002924906,0.00005649008,0.0000928768,0.00006267821,0.00002199223,0.00003113281,0.000989845,0.00004873459,0.00002133851],"category_scores_gemma":[0.00009702345,0.00002308742,0.00001983895,0.0002040952,0.00006237899,0.0001500422,0.0002504186,0.0001103504,0.000005474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009450495,"about_ca_system_score_gemma":0.00001600783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001239753,"about_ca_topic_score_gemma":0.0001765948,"domain_scores_codex":[0.9994594,0.00005619926,0.000117667,0.0001543146,0.00008682926,0.0001255509],"domain_scores_gemma":[0.9993917,0.0001180073,0.00004808211,0.0003962505,0.0000331101,0.0000128798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003643345,0.00002501737,0.001448373,0.00001816171,0.00000343226,0.000002010862,0.0008608964,0.000001180879,0.00918422,0.4321249,0.001143442,0.5551847],"study_design_scores_gemma":[0.0001765042,0.00006534199,0.001567879,0.0000321607,0.000001769314,0.00000918299,0.00003792357,0.01187799,0.3248331,0.6577662,0.003486261,0.0001457173],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05722082,0.000732729,0.9238787,0.01066111,0.0005677328,0.0001873782,5.931405e-7,0.0006116863,0.006139293],"genre_scores_gemma":[0.8556236,0.000004299936,0.1432694,0.0005139771,0.0000165166,0.000004632121,1.269043e-7,0.000002331178,0.0005650799],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7984028,"threshold_uncertainty_score":0.1839395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007043832333426662,"score_gpt":0.25139587543639,"score_spread":0.2443520431029633,"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."}}