{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00303405,0.001726153,0.001497201,0.004436281,0.002321131,0.002429773,0.003719499,0.001555656,0.03183843],"category_scores_gemma":[0.007903581,0.0007624602,0.00113493,0.002316562,0.0008780546,0.003966424,0.003797364,0.002051183,0.04217165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00218651,"about_ca_system_score_gemma":0.00448693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07971243,"about_ca_topic_score_gemma":0.099435,"domain_scores_codex":[0.996329,0.0004555342,0.0002659919,0.001073004,0.001507465,0.0003689329],"domain_scores_gemma":[0.9949809,0.0006355654,0.0002256781,0.00161465,0.002150541,0.0003926209],"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":[0.0004654991,0.0002677594,0.007251416,0.0006654956,0.000124027,0.0005083805,0.0007197017,0.002627336,0.03435125,0.007873061,0.4038388,0.5413072],"study_design_scores_gemma":[0.0002237844,0.0004149759,0.0164771,0.000282992,0.0002422713,0.003425297,0.001066986,0.1988267,0.07175939,0.01405858,0.6926385,0.000583462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.04353904,0.001572891,0.3621772,0.001081204,0.0008224025,0.001874131,0.05813441,0.448552,0.08224675],"genre_scores_gemma":[0.1872673,0.0006093086,0.5792931,0.001175954,0.0002317883,0.001152959,0.1624483,0.01306871,0.05475259],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.07971243,"threshold_uncertainty_score":0.1584969,"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."}}