{"id":"W2807182733","doi":"10.18653/v1/w18-1605","title":"Cross-corpus Native Language Identification via Statistical Embedding","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"Qatar National Research Fund; Fonds National de la Recherche Luxembourg; Qatar Foundation","keywords":"Computer science; Natural language processing; Artificial intelligence; Identification (biology); Task (project management); Embedding; Language identification; Indonesian; Arabic; Representation (politics); Language model; Linguistics; Natural language; Engineering","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":[0.001996066,0.001307061,0.0008169693,0.001734119,0.0004660677,0.00147486,0.001002239,0.0009225726,0.002363527],"category_scores_gemma":[0.006573809,0.0004086744,0.00065231,0.0011192,0.0005302097,0.003500518,0.002508623,0.001427108,0.002487726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002852489,"about_ca_system_score_gemma":0.0007486602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00166957,"about_ca_topic_score_gemma":0.002549638,"domain_scores_codex":[0.9985,0.0005201254,0.00008756875,0.0005303073,0.0002429472,0.0001190639],"domain_scores_gemma":[0.9966185,0.001526799,0.0002210854,0.000804272,0.0007256886,0.0001036113],"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":[0.0005945941,0.0004998306,0.009243605,0.0002467882,0.0003439485,0.0006539936,0.0006033952,0.08371542,0.06974175,0.005883903,0.005748516,0.8227242],"study_design_scores_gemma":[0.00001756191,0.0002154105,0.004357282,0.00003131857,0.00007371213,0.0005721138,0.0003738117,0.9441694,0.03439653,0.009664328,0.006058739,0.00006972352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1675241,0.001058299,0.8192638,0.0003243314,0.0002394491,0.0001041327,0.0006579639,0.006371481,0.004456502],"genre_scores_gemma":[0.784609,0.0004550607,0.201842,0.0002301192,0.0001488808,0.0001439064,0.003555448,0.0007238092,0.008291667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002363527,"threshold_uncertainty_score":0.01055634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01119138976994625,"score_gpt":0.3515243750749443,"score_spread":0.340332985304998,"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."}}