{"id":"W2251071163","doi":"10.3115/v1/w14-5316","title":"The NRC System for Discriminating Similar Languages","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Discriminative model; Classifier (UML); Artificial intelligence; Natural language processing; Generative grammar; Voting; Group (periodic table); Task (project management); Feature (linguistics); F1 score; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008769244,0.00007962143,0.00007834494,0.00002456202,0.0003080298,0.0003008528,0.0009563251,0.00003312445,5.454277e-7],"category_scores_gemma":[0.0004363049,0.00004273234,0.00004127617,0.00009557325,0.00002352447,0.000196538,0.0001748786,0.0000630639,0.000004157547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000381932,"about_ca_system_score_gemma":0.00001488547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001800266,"about_ca_topic_score_gemma":0.00001672237,"domain_scores_codex":[0.99926,0.00004084784,0.00011924,0.0001855957,0.0001963761,0.0001979145],"domain_scores_gemma":[0.9989744,0.0004138798,0.00006028658,0.000394657,0.0001276986,0.00002909415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.456715e-7,0.000002588241,0.000005523786,0.00004378819,0.000002418172,6.268743e-7,0.000149269,6.101156e-7,0.0009956135,0.8179029,0.001792744,0.179103],"study_design_scores_gemma":[0.0005102223,0.0002470105,0.00005303782,0.0002827794,0.00002388324,0.00005671772,0.001769644,0.4185214,0.3704878,0.1501283,0.0571919,0.0007272678],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001155309,0.0006231433,0.9888159,0.00197871,0.0001257431,0.0001483745,5.071753e-7,0.001034572,0.007157512],"genre_scores_gemma":[0.5189701,8.916368e-7,0.4802804,0.0001790732,0.00006722024,0.00003078117,3.808419e-7,0.000005564638,0.0004655603],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6677746,"threshold_uncertainty_score":0.290113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009560383488284923,"score_gpt":0.2752821631446367,"score_spread":0.2657217796563517,"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."}}