{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004396651,0.0001387051,0.0001405848,0.0001122699,0.000108977,0.0001526498,0.0008042067,0.0000816438,0.00001901163],"category_scores_gemma":[0.00006984345,0.0001050584,0.00004651564,0.0003881679,0.00002718134,0.0006035995,0.0001501555,0.000234695,0.0000817352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006169733,"about_ca_system_score_gemma":0.00002447218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000513069,"about_ca_topic_score_gemma":0.000006092243,"domain_scores_codex":[0.998864,0.00005747741,0.0001483773,0.0002317272,0.0003341773,0.0003642261],"domain_scores_gemma":[0.9991692,0.00007420141,0.0000583321,0.0005225296,0.00005662036,0.0001191236],"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":[0.00005521828,0.0008020287,0.04317875,0.00007997343,0.00003594576,0.00003021527,0.001748132,0.0002982037,0.006214685,0.4187046,0.01178469,0.5170676],"study_design_scores_gemma":[0.00147987,0.000275202,0.01008692,0.0006119023,0.00003479657,0.00005440702,0.00007390638,0.5402551,0.3885892,0.03133469,0.02503607,0.002167965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006463857,0.001014307,0.9739147,0.000554945,0.0003785439,0.0001235073,1.719921e-7,0.002125187,0.01542479],"genre_scores_gemma":[0.6919667,8.262255e-7,0.3072083,0.0005434701,0.00003993768,0.000007552763,9.341181e-7,0.000007740031,0.0002246033],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6855028,"threshold_uncertainty_score":0.4284156,"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."}}