{"id":"W43028483","doi":"10.63317/4wof6fn4wqjp","title":"NLGbAse: A Free Linguistic Resource for Natural Language Processing Systems","year":2010,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Metadata; Annotation; Natural language processing; Context (archaeology); Artificial intelligence; Domain (mathematical analysis); Natural language; Resource (disambiguation); Field (mathematics); Information retrieval; World Wide Web","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":[0.00461794,0.002152645,0.00218468,0.006934549,0.001865421,0.004173792,0.004476358,0.003097374,0.04738995],"category_scores_gemma":[0.02610101,0.002101975,0.001214434,0.005525252,0.001328663,0.009782952,0.007362831,0.003459621,0.05093187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001570335,"about_ca_system_score_gemma":0.0035446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005449686,"about_ca_topic_score_gemma":0.006860369,"domain_scores_codex":[0.9964562,0.0009452146,0.0006385598,0.0005951442,0.001164048,0.0002008011],"domain_scores_gemma":[0.9848157,0.007616879,0.001101642,0.003604538,0.002069572,0.0007916192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009760351,0.000238377,0.001108302,0.00428166,0.0001925273,0.001421986,0.001408165,0.002577061,0.02080427,0.01722814,0.8219476,0.1278159],"study_design_scores_gemma":[0.0003651357,0.0001081909,0.002127714,0.0005043096,0.00007859536,0.001117921,0.000284756,0.01223746,0.0200389,0.02243437,0.9404384,0.0002641899],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.004693298,0.001058368,0.2365499,0.001333478,0.0005216927,0.00151185,0.2250648,0.5074107,0.02185592],"genre_scores_gemma":[0.02518186,0.0008874528,0.3080407,0.001009813,0.0002020244,0.003747467,0.5901749,0.05835465,0.01240121],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.04738995,"threshold_uncertainty_score":0.1585352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01258552495269672,"score_gpt":0.2918051607984203,"score_spread":0.2792196358457236,"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."}}