{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002860358,0.00008002476,0.0001150112,0.00003125111,0.00008632751,0.00006188982,0.0006345948,0.0000340807,0.00004713538],"category_scores_gemma":[0.00004432426,0.00005532127,0.00004414147,0.0001363197,0.0000359041,0.0001801478,0.0001057039,0.00006761045,0.000002969239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008792578,"about_ca_system_score_gemma":0.00005347828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002450364,"about_ca_topic_score_gemma":0.0001068318,"domain_scores_codex":[0.9992003,0.00002206657,0.0002209056,0.0002199612,0.0001475447,0.0001892472],"domain_scores_gemma":[0.9991509,0.0002228543,0.0000756993,0.0004275454,0.0001026249,0.00002041629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003254529,0.0007194,0.164623,0.0008256852,0.0001037083,0.00001245243,0.005969058,0.009947898,0.002937661,0.4243569,0.05710492,0.3333668],"study_design_scores_gemma":[0.0004508133,0.00004748113,0.008370388,0.00001861116,0.000007827242,0.000003612358,0.00002717847,0.9698846,0.004838173,0.009041367,0.007118827,0.0001911247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1073654,0.0000164418,0.8878406,0.0003104341,0.0001571583,0.0001624745,0.000008237759,0.0000460384,0.00409323],"genre_scores_gemma":[0.9325408,4.405145e-7,0.06680334,0.0002406463,0.00004211819,0.000009814113,0.000002724478,0.000002789114,0.000357324],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9599367,"threshold_uncertainty_score":0.2255936,"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."}}