{"id":"W2362196274","doi":"","title":"Algorithm Research for Semi-structured Text Information Extraction Based on Hidden Markov Model","year":2014,"lang":"en","type":"article","venue":"Electronic Science and Technology","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec","funders":"","keywords":"Hidden Markov model; Information extraction; Computer science; Precision and recall; Recall; Recall rate; Forward algorithm; Maximum-entropy Markov model; Markov chain; Algorithm; Markov model; Data mining; State (computer science); Artificial intelligence; Machine learning; Variable-order Markov model","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":[0.001463708,0.0008594905,0.001306794,0.002173758,0.0006943975,0.001283964,0.001536245,0.0009281563,0.002295036],"category_scores_gemma":[0.003921184,0.0005169553,0.001152092,0.001981727,0.0005170731,0.002998198,0.001020383,0.001185626,0.0009977882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007775427,"about_ca_system_score_gemma":0.002127058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003115293,"about_ca_topic_score_gemma":0.002310739,"domain_scores_codex":[0.998455,0.0003556475,0.0001928335,0.0003924959,0.0005220086,0.00008192608],"domain_scores_gemma":[0.9983252,0.0008754774,0.0001340395,0.0001341949,0.0004907126,0.00004044537],"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":[0.0002495199,0.00009826962,0.001833008,0.0006494158,0.0002326092,0.0002226042,0.000273167,0.09869862,0.01503134,0.02758516,0.006674333,0.848452],"study_design_scores_gemma":[0.00007032134,0.00006879048,0.0005390013,0.00004320217,0.0000735092,0.0003366516,0.00005009872,0.968325,0.009444343,0.01600366,0.004999686,0.00004580075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002036912,0.0003527153,0.9965402,0.00009545276,0.00004136525,0.00005613476,0.00005027743,0.0005513171,0.0002757367],"genre_scores_gemma":[0.08572328,0.001291057,0.9093099,0.0001451652,0.0001135425,0.0004392702,0.0007677798,0.0001075541,0.00210251],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003115293,"threshold_uncertainty_score":0.007740915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01495039204103521,"score_gpt":0.3356443404495095,"score_spread":0.3206939484084743,"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."}}