{"id":"W1560635010","doi":"10.1023/a:1007653929870","title":"Stochastic Grammatical Inference of Text Database Structure","year":2000,"lang":"en","type":"article","venue":"Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Grammar induction; Computer science; Nesting (process); Markup language; Inference; Construct (python library); Semantics (computer science); Grammar; Artificial intelligence; Natural language processing; Theoretical computer science; Programming language; XML; Rule-based machine translation; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003454792,0.0003565935,0.0008878899,0.002170717,0.001063931,0.002305386,0.002358176,0.001476493,0.004576388],"category_scores_gemma":[0.03300841,0.0009271363,0.001384373,0.001706111,0.00133112,0.006336168,0.001866048,0.002023964,0.0008856315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002040903,"about_ca_system_score_gemma":0.001907842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007129606,"about_ca_topic_score_gemma":0.01278271,"domain_scores_codex":[0.9971797,0.001208685,0.0002351979,0.0005819648,0.0006152524,0.0001790915],"domain_scores_gemma":[0.9683925,0.02529387,0.001053545,0.002208408,0.002740875,0.0003107574],"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":[0.0004688418,0.0002717508,0.009204257,0.0005669422,0.0001753562,0.0004959423,0.0009694526,0.215421,0.008545945,0.494464,0.02019027,0.2492263],"study_design_scores_gemma":[0.0000262237,0.00001520855,0.0004806235,0.00001962441,0.00003123964,0.00005981208,0.00005819082,0.7679944,0.002217041,0.2276213,0.00146197,0.0000144092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07095329,0.0002342062,0.9199224,0.002054723,0.0001259293,0.00006998386,0.001292829,0.002318564,0.003028084],"genre_scores_gemma":[0.7457427,0.0003030306,0.2467407,0.0004863538,0.0002699102,0.0001161711,0.002746617,0.0005805786,0.003013992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007129606,"threshold_uncertainty_score":0.01827091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008191670648523592,"score_gpt":0.2716978941340115,"score_spread":0.2635062234854879,"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."}}