{"id":"W2045929671","doi":"10.1145/1376815.1376819","title":"Semantic text similarity using corpus-based word similarity and string similarity","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Topic Modeling","field":"Computer Science","cited_by":485,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Similarity (geometry); Semantic similarity; String metric; Artificial intelligence; Word (group theory); Natural language processing; Longest common subsequence problem; Focus (optics); String searching algorithm; String (physics); Representation (politics); Information retrieval; Matching (statistics); Pattern matching; Mathematics; Algorithm","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":[0.002177997,0.00092376,0.001464652,0.01774631,0.0009860167,0.002976211,0.001630763,0.001285142,0.003514882],"category_scores_gemma":[0.01814917,0.000312062,0.001163446,0.01682147,0.001240919,0.005136708,0.002024637,0.00100161,0.001902967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009804009,"about_ca_system_score_gemma":0.001356322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001658718,"about_ca_topic_score_gemma":0.001637855,"domain_scores_codex":[0.9943928,0.001124886,0.0007004199,0.001007105,0.002637846,0.0001368597],"domain_scores_gemma":[0.9921194,0.003030686,0.0009637382,0.00113907,0.00249476,0.0002522486],"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":[0.0005017755,0.0004054433,0.01289896,0.001379963,0.0005654665,0.0004173881,0.001131468,0.02129064,0.02876124,0.05392328,0.01116528,0.8675591],"study_design_scores_gemma":[0.0001940287,0.0009286882,0.02707705,0.0004368933,0.0005551387,0.002814416,0.001698498,0.6720217,0.04891734,0.1823989,0.06249095,0.0004662709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05191324,0.002126402,0.930313,0.0002680698,0.0004651728,0.0006221626,0.00230973,0.002587464,0.009394729],"genre_scores_gemma":[0.2841628,0.001106184,0.7038279,0.000128194,0.0005406998,0.001079478,0.00547775,0.0004178632,0.003259144],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01774631,"threshold_uncertainty_score":0.01175845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1204337695552436,"score_gpt":0.3074205502158795,"score_spread":0.186986780660636,"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."}}