{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004279114,0.000448995,0.0004991243,0.0002411639,0.0008887696,0.0003913397,0.003230168,0.0002317603,0.00004392673],"category_scores_gemma":[0.0001673055,0.0004738807,0.0001300574,0.0006018268,0.0002230122,0.003200896,0.0004491765,0.000779875,0.00002848651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552863,"about_ca_system_score_gemma":0.000453603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009395767,"about_ca_topic_score_gemma":0.001253196,"domain_scores_codex":[0.996618,0.000222386,0.0005515344,0.001596256,0.0004451674,0.0005666909],"domain_scores_gemma":[0.9936689,0.0007663651,0.0001452886,0.005073285,0.0001057097,0.0002404396],"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":[0.001053573,0.01423526,0.08035918,0.00132997,0.002046416,0.001244942,0.009301427,0.1438239,0.0135037,0.005221042,0.003561208,0.7243194],"study_design_scores_gemma":[0.001520633,0.00007072123,0.00786985,0.0002232161,0.0001557927,0.00003782412,0.00005887906,0.9804195,0.00405095,0.003056296,0.00167967,0.0008566504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2578979,0.0004820103,0.7391785,0.000449269,0.000602322,0.000255162,0.0008822596,0.0002009372,0.00005164174],"genre_scores_gemma":[0.9141459,0.0001758536,0.08496581,0.000283262,0.0001203571,0.000007870697,0.0001857914,0.00003426243,0.00008088908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8365957,"threshold_uncertainty_score":0.9997713,"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."}}