{"id":"W2144630894","doi":"10.1007/s10844-005-0861-z","title":"Post-Supervised Template Induction for Information Extraction from Lists and Tables in Dynamic Web Sources","year":2005,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Row; Machine learning; Data mining; Artificial intelligence; Dynamic programming; Supervised learning; Exploit; Information extraction; Unsupervised learning; Row and column spaces; Pattern recognition (psychology); Information retrieval; Algorithm; Database; Artificial neural network","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":[0.001847651,0.001158675,0.001475934,0.006852447,0.001332252,0.002130615,0.002776451,0.001601572,0.005792176],"category_scores_gemma":[0.008698764,0.0009154249,0.002182258,0.006612774,0.000728832,0.003833742,0.001860369,0.001610818,0.007070547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009410227,"about_ca_system_score_gemma":0.003583924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005343763,"about_ca_topic_score_gemma":0.01038548,"domain_scores_codex":[0.9980123,0.0003539316,0.0002726688,0.0005484342,0.000627723,0.0001849267],"domain_scores_gemma":[0.9922516,0.004099844,0.0005878345,0.001307745,0.001547319,0.0002057085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003700226,0.000276894,0.004875461,0.000700468,0.0001542041,0.0005648833,0.000341124,0.009101298,0.02239806,0.006334269,0.02634237,0.9285409],"study_design_scores_gemma":[0.0001310795,0.0002575979,0.005995976,0.0002169765,0.0004823359,0.001367594,0.0006372416,0.7902204,0.1105617,0.04768267,0.04231462,0.0001318182],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01731248,0.0007059392,0.9506807,0.0003116849,0.0001041329,0.0003657209,0.005603068,0.02338484,0.001531519],"genre_scores_gemma":[0.1102483,0.000573981,0.8583773,0.0001367313,0.0001178225,0.0003950212,0.02522999,0.001163075,0.003757755],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006852447,"threshold_uncertainty_score":0.01937675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01489196065337485,"score_gpt":0.2572530941832417,"score_spread":0.2423611335298668,"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."}}