{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001086712,0.0008210334,0.001267591,0.006289562,0.0007657015,0.002345429,0.001394722,0.0008771402,0.002863675],"category_scores_gemma":[0.00456806,0.000404112,0.001367951,0.005029664,0.0006326663,0.004395349,0.001076923,0.001124256,0.00212471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000495221,"about_ca_system_score_gemma":0.001054263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00153441,"about_ca_topic_score_gemma":0.002137823,"domain_scores_codex":[0.998866,0.0001764274,0.0001714454,0.0003088783,0.0004024327,0.00007485976],"domain_scores_gemma":[0.9973795,0.001505071,0.0001514199,0.0002685454,0.0006296703,0.00006569154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003447761,0.0002308545,0.002196637,0.0006184471,0.0001345643,0.0002464209,0.0004133514,0.005552393,0.03559736,0.01489114,0.01050636,0.9292678],"study_design_scores_gemma":[0.0001403536,0.0003694496,0.004972304,0.0002871471,0.0005791167,0.002145212,0.0007332677,0.7113154,0.1034907,0.1223348,0.05349167,0.0001405598],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02882103,0.001992537,0.958085,0.0004109722,0.0001800151,0.0002372622,0.001734853,0.005125575,0.00341277],"genre_scores_gemma":[0.1168732,0.001400552,0.8707542,0.0001334116,0.0002116155,0.0002016875,0.006436192,0.0003729258,0.003616188],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006289562,"threshold_uncertainty_score":0.009579957,"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."}}