{"id":"W1535872236","doi":"10.1007/978-3-642-39736-3_16","title":"Matching Semi-structured Documents Using Similarity of Regions through Fuzzy Rule-Based System","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Information retrieval; Fuzzy logic; Similarity (geometry); Categorization; Set (abstract data type); Artificial intelligence; Matching (statistics); Data mining; Representation (politics); Similarity measure; Semantic similarity; Metric (unit); Natural language processing; Image (mathematics); 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":[0.0004768232,0.0005909287,0.0007214052,0.0007684485,0.0003609083,0.000584826,0.004250269,0.0005296897,0.00001719163],"category_scores_gemma":[0.00004788126,0.0005241996,0.0001895447,0.0007996483,0.0009029076,0.001209156,0.001316651,0.0007738443,0.00002063162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005842803,"about_ca_system_score_gemma":0.0005472907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001650248,"about_ca_topic_score_gemma":0.00002116708,"domain_scores_codex":[0.9959043,0.00005266475,0.0008372812,0.001428764,0.001147155,0.0006298273],"domain_scores_gemma":[0.9961713,0.0003234944,0.0008712738,0.002198948,0.0003298064,0.0001051735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001118715,0.00006719839,0.0002407395,0.0005248039,0.00005389812,0.00005460528,0.00138431,0.08370632,0.003435368,0.7815934,0.00007829855,0.1288499],"study_design_scores_gemma":[0.0004360497,0.00008354527,0.0001361558,0.001189622,0.0000233369,0.00004413056,0.000003802105,0.2606641,0.01101124,0.7251236,0.0004500456,0.0008343519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001026482,0.0002629551,0.9934348,0.0005797739,0.001275275,0.0005825085,0.00001009772,0.0005495916,0.002278529],"genre_scores_gemma":[0.5306166,0.00001125458,0.4688825,0.0002821274,0.00008206144,0.000009823664,0.000005056352,0.00002464783,0.00008596321],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5295901,"threshold_uncertainty_score":0.9997209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03146047213649442,"score_gpt":0.2695239977017202,"score_spread":0.2380635255652258,"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."}}