{"id":"W2543556230","doi":"10.1109/nlpke.2003.1275910","title":"Fuzzy semantic measurement for synonymy and its npplication in an automatic question-answering system","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Semantics (computer science); Natural language processing; Closeness; Sentence; Information retrieval; Question answering; Artificial intelligence; Construct (python library); Measure (data warehouse); Fuzzy logic; Semantic similarity; Novelty; Data mining; Mathematics; Programming language","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":[0.005919307,0.0004642757,0.000943768,0.004206993,0.001155232,0.002717803,0.001143906,0.001006973,0.001503596],"category_scores_gemma":[0.02122922,0.0003278671,0.0005843282,0.002886534,0.001708428,0.005458221,0.001456897,0.0009026328,0.0003355725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001066405,"about_ca_system_score_gemma":0.0007943424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001073843,"about_ca_topic_score_gemma":0.0009364969,"domain_scores_codex":[0.9920931,0.003478587,0.0006561118,0.001116655,0.002471812,0.0001836563],"domain_scores_gemma":[0.9890445,0.007317366,0.0009683326,0.0009918266,0.001427966,0.0002499491],"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":[0.001043302,0.0004946889,0.01630334,0.0007541149,0.0002889196,0.0005149969,0.009226402,0.02133592,0.1474362,0.2146813,0.002409247,0.5855116],"study_design_scores_gemma":[0.0001163494,0.0007534739,0.01596296,0.0001053652,0.0002142169,0.0009746075,0.002204753,0.6582788,0.08091089,0.2302788,0.01000562,0.0001940895],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1434024,0.0002785172,0.8530746,0.0002812826,0.00002320152,0.0001219331,0.0002263167,0.0008787033,0.00171317],"genre_scores_gemma":[0.6188812,0.00007259132,0.3801441,0.00005243247,0.00003813539,0.0001937213,0.0002489238,0.00005103332,0.0003178412],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005919307,"threshold_uncertainty_score":0.03130466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02273217025668899,"score_gpt":0.2858214549272483,"score_spread":0.2630892846705593,"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."}}