{"id":"W2756560861","doi":"10.63317/2aovvs53yg45","title":"Second Order Co-occurrence PMI for Determining the Semantic Similarity of Words","year":2006,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Semantic similarity; Natural language processing; Similarity (geometry); Computer science; Synonym (taxonomy); Artificial intelligence; Pointwise; Noun; Pointwise mutual information; Semantics (computer science); Test (biology); Linguistics; Mathematics; Mutual information","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":[0.004386414,0.001530169,0.001645769,0.01902184,0.001487682,0.001956275,0.001945047,0.001302465,0.002894202],"category_scores_gemma":[0.02215344,0.0007015183,0.001738323,0.01275703,0.001126316,0.004260012,0.001748749,0.001780958,0.00198606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001468264,"about_ca_system_score_gemma":0.001730898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004384268,"about_ca_topic_score_gemma":0.004798499,"domain_scores_codex":[0.9935946,0.001553935,0.0005052874,0.00160586,0.00251035,0.0002299509],"domain_scores_gemma":[0.9864325,0.008654254,0.001080915,0.00155889,0.001956457,0.000316982],"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":[0.001150803,0.0003910701,0.06472015,0.001356429,0.001038789,0.0005840396,0.001974946,0.02453501,0.02158907,0.01884346,0.01334991,0.8504664],"study_design_scores_gemma":[0.0001363339,0.0003926988,0.08175416,0.0001981267,0.0004497057,0.003375042,0.000886724,0.82963,0.02063095,0.03934941,0.02272285,0.0004739708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05635631,0.001514465,0.9298539,0.0001658281,0.0001866077,0.0006820117,0.003662171,0.002834165,0.004744565],"genre_scores_gemma":[0.384034,0.0006388266,0.605056,0.00005173698,0.0003161457,0.001955192,0.005914492,0.0004598898,0.001573668],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01902184,"threshold_uncertainty_score":0.02319783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03016811658200047,"score_gpt":0.2817826913225887,"score_spread":0.2516145747405882,"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."}}