{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008302441,0.0005594317,0.0005960951,0.0003343724,0.0002550381,0.001776007,0.005427619,0.0007330464,0.000004433806],"category_scores_gemma":[0.001837871,0.0004593687,0.0002174514,0.0002893985,0.00009064286,0.0002376342,0.003696087,0.002165831,0.000005449088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001315447,"about_ca_system_score_gemma":0.0004318318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002879136,"about_ca_topic_score_gemma":0.00006029785,"domain_scores_codex":[0.9968435,0.00007546193,0.0005718889,0.001287951,0.0005856922,0.0006355604],"domain_scores_gemma":[0.9960903,0.0002642128,0.0005316968,0.002408609,0.0005511173,0.0001540724],"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":[0.0001622096,0.0004310842,0.00003930095,0.02236919,0.0002537112,0.0007244,0.01869554,0.0002132096,0.01978289,0.2544686,0.0687475,0.6141124],"study_design_scores_gemma":[0.0007672427,0.00009649041,0.000005639578,0.002504406,0.00009576035,0.0001752574,0.0001690595,0.896556,0.015373,0.05744729,0.02474188,0.002068033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004151239,0.05508585,0.9336955,0.0007215945,0.002273414,0.001443939,0.00005006271,0.004258318,0.002056199],"genre_scores_gemma":[0.3180609,0.00000341078,0.67756,0.0003328082,0.001018358,0.0003082904,0.000069554,0.0000605549,0.002586091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8963428,"threshold_uncertainty_score":0.9999535,"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."}}