{"id":"W2026355363","doi":"10.1145/1871437.1871527","title":"Index structures for efficiently searching natural language text","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Parsing; Index (typography); Scalability; Class (philosophy); Phrase; Natural language; Construct (python library); Granularity; Information retrieval; Question answering; Parse tree; Word (group theory); Term (time); Natural language processing; Artificial intelligence; Data mining; Database; World Wide Web; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001419003,0.00007878472,0.00007058034,0.00005921863,0.0001549982,0.0002184527,0.0007557992,0.00003922078,0.00003791202],"category_scores_gemma":[0.00004723801,0.00005306461,0.00003793557,0.0001019388,0.00002292766,0.0003055672,0.0003485369,0.0002236972,0.00001143423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004805045,"about_ca_system_score_gemma":0.00002676857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000716603,"about_ca_topic_score_gemma":0.00003863257,"domain_scores_codex":[0.999262,0.00001124508,0.00008517809,0.0002452948,0.0001824027,0.000213921],"domain_scores_gemma":[0.9993584,0.0000976373,0.00002677786,0.000415289,0.00003760298,0.00006432476],"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":[0.00001177704,0.00003750554,0.0002815632,0.00001619094,0.000009294837,0.000007848781,0.00115752,0.00009683039,0.06752697,0.147425,0.005910661,0.7775188],"study_design_scores_gemma":[0.0004333376,0.00003412361,0.007439021,0.000005500318,0.000001433697,0.00001513833,0.00007584834,0.9647626,0.01212716,0.003181521,0.01173286,0.0001914473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1661196,0.00005487274,0.8313465,0.000208468,0.0009662613,0.000145943,0.000006835216,0.0001454989,0.001005996],"genre_scores_gemma":[0.8390181,2.524448e-7,0.1601323,0.0002036569,0.0001352089,0.000004265183,0.000008135302,0.00000447855,0.0004935948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9646658,"threshold_uncertainty_score":0.2163912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006454486159736561,"score_gpt":0.2758822414130412,"score_spread":0.2694277552533047,"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."}}