{"id":"W2250351693","doi":"","title":"Comparing Word Relatedness Measures Based on Google $n$-grams","year":2012,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Word (group theory); Natural language processing; n-gram; Artificial intelligence; Text corpus; Point (geometry); Language model; Information retrieval; Mathematics","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":[0.004111827,0.001121981,0.001224737,0.01783472,0.0009508101,0.001927788,0.0009812971,0.001241219,0.001847044],"category_scores_gemma":[0.03187051,0.0002844222,0.0009868151,0.0126592,0.0007324032,0.004848326,0.00196547,0.0008052069,0.001813246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001002164,"about_ca_system_score_gemma":0.0007967303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005028135,"about_ca_topic_score_gemma":0.009637434,"domain_scores_codex":[0.9943321,0.001843502,0.00075124,0.0007467118,0.002082079,0.0002444047],"domain_scores_gemma":[0.9832844,0.01003605,0.001546526,0.001746965,0.002956223,0.0004297474],"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":[0.003257867,0.001186778,0.1458366,0.003200075,0.001877437,0.0006891497,0.002540816,0.03411113,0.02896144,0.01484318,0.04214789,0.7213476],"study_design_scores_gemma":[0.0004014848,0.002460009,0.3564973,0.0004764668,0.0008990153,0.003391852,0.00510401,0.4886434,0.05058876,0.04375855,0.04710932,0.0006696945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9059611,0.006536846,0.05528564,0.0003925315,0.0004245645,0.0004602387,0.009414127,0.004323992,0.01720098],"genre_scores_gemma":[0.8421555,0.001595592,0.1253693,0.0001295014,0.0001877475,0.0005021362,0.02638518,0.0005402806,0.003134752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01783472,"threshold_uncertainty_score":0.02174568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03840143162589264,"score_gpt":0.2762720713499136,"score_spread":0.2378706397240209,"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."}}