{"id":"W1841070547","doi":"10.1007/11892755_86","title":"Document Mining Based on Semantic Understanding of Text","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Semantic similarity; Representation (politics); Information retrieval; Measure (data warehouse); Semantic computing; Similarity (geometry); Natural language processing; Similarity measure; Matching (statistics); Cluster analysis; Explicit semantic analysis; Semantic matching; Data mining; Artificial intelligence; Semantic technology; Semantic Web; Image (mathematics)","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"],"consensus_categories":[],"category_scores_codex":[0.0009376959,0.0004260495,0.0005722745,0.001407712,0.0002017892,0.0003948121,0.002528503,0.0001859952,0.00001889148],"category_scores_gemma":[0.00006022533,0.0003799716,0.0001751032,0.0008298663,0.0004686836,0.000327732,0.0006142022,0.000396612,0.0000146773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004099699,"about_ca_system_score_gemma":0.0003882821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004837723,"about_ca_topic_score_gemma":0.00004620421,"domain_scores_codex":[0.9964288,0.00003702448,0.0005586827,0.001271781,0.001196323,0.0005073443],"domain_scores_gemma":[0.9972369,0.000701935,0.0003958819,0.001466065,0.00009567199,0.0001035222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001055435,0.00008449428,0.0003279346,0.000137162,0.00003890882,0.0001756515,0.0006322779,0.6898197,0.0001615004,0.04166951,0.0003269877,0.2666153],"study_design_scores_gemma":[0.000245075,0.0001997355,0.00005320424,0.001003846,0.00001996515,0.000008205256,5.12774e-7,0.9636049,0.0007849046,0.03335608,0.0002454594,0.0004780771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00008260711,0.00008095447,0.9910838,0.0005517024,0.0005382907,0.0001258142,0.000005903787,0.00007785247,0.007453093],"genre_scores_gemma":[0.7412418,0.000005472233,0.2576858,0.0005903779,0.0001534452,0.000002250345,0.00001057873,0.00002269425,0.0002875636],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7411592,"threshold_uncertainty_score":0.9998652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0259208407772317,"score_gpt":0.2463079150113822,"score_spread":0.2203870742341505,"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."}}