{"id":"W1633328346","doi":"10.1007/978-3-642-21043-3_26","title":"Comparison of Semantic Similarity for Different Languages Using the Google n-gram Corpus and Second-Order Co-occurrence Measures","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Natural language processing; Similarity (geometry); German; Semantic similarity; Artificial intelligence; Word (group theory); n-gram; Word order; Language model; Linguistics","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":[0.0007324304,0.0004380598,0.0006906614,0.0003015125,0.0002940827,0.0002680059,0.002261539,0.0002292146,0.000009660749],"category_scores_gemma":[0.0001196934,0.0003146593,0.000107743,0.0002137239,0.0007736257,0.0002525889,0.0008383569,0.0005777596,8.150985e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008531615,"about_ca_system_score_gemma":0.0002529222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005189703,"about_ca_topic_score_gemma":0.0002644625,"domain_scores_codex":[0.9971518,0.00005449769,0.0005739175,0.001062954,0.000663876,0.0004929724],"domain_scores_gemma":[0.9973121,0.0006936115,0.0004434244,0.001152054,0.0002926371,0.0001061426],"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":[0.00002545909,0.0001559989,0.006198498,0.0005520083,0.00006904826,0.0000157341,0.008336565,0.0230983,0.001443582,0.03105867,0.00004776357,0.9289984],"study_design_scores_gemma":[0.0002866678,0.0001734773,0.0004540001,0.0003573878,0.00002961526,0.00003288587,0.000002462875,0.9506561,0.006278711,0.04075865,0.0004465042,0.0005235915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004228949,0.001380272,0.9926118,0.0001376178,0.0006616391,0.0006121172,0.00003507217,0.00005967477,0.0002728791],"genre_scores_gemma":[0.8342357,0.00002545069,0.1652447,0.0002883423,0.0001351886,0.00000876646,0.000005302054,0.00001736004,0.00003919554],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9284748,"threshold_uncertainty_score":0.9999306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07990233339630563,"score_gpt":0.3274145852463676,"score_spread":0.247512251850062,"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."}}