{"id":"W2251547673","doi":"10.63317/54n4hrwwu9u9","title":"Measuring Interlanguage: Native Language Identification with L1-influence Metrics","year":2012,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Bigram; Natural language processing; Artificial intelligence; Interlanguage; Identification (biology); Language identification; Word (group theory); Machine translation; Task (project management); Natural language; Linguistics","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":[0.006100823,0.001022013,0.0008026674,0.005994332,0.00140927,0.002521463,0.0007896383,0.001074,0.002216503],"category_scores_gemma":[0.0432542,0.0003764336,0.000483166,0.003247987,0.00145218,0.004769775,0.002939338,0.001164732,0.001759491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007921767,"about_ca_system_score_gemma":0.000794919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002819361,"about_ca_topic_score_gemma":0.004426499,"domain_scores_codex":[0.9925483,0.002730041,0.0007006529,0.001471958,0.002193042,0.000356011],"domain_scores_gemma":[0.9634334,0.02079859,0.003664036,0.003293955,0.007278503,0.001531411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0009342331,0.0007908223,0.2856309,0.001083242,0.0004759729,0.0006293607,0.008173423,0.01133686,0.04765482,0.00445943,0.007868769,0.6309621],"study_design_scores_gemma":[0.0001075986,0.001542239,0.4994676,0.0002150031,0.0003920887,0.00329589,0.004500233,0.2858885,0.1641787,0.01460475,0.0253475,0.0004597501],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7376028,0.001559349,0.233778,0.000261107,0.0001044795,0.000318557,0.001942106,0.003425353,0.02100818],"genre_scores_gemma":[0.9425898,0.0002079643,0.05244001,0.00007065827,0.00008117087,0.0002692483,0.002019753,0.0006404348,0.001681082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006100823,"threshold_uncertainty_score":0.03226459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01889991639026808,"score_gpt":0.2762415163566559,"score_spread":0.2573415999663878,"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."}}