{"id":"W2603222250","doi":"10.1017/s0269888917000029","title":"The state of the art in semantic relatedness: a framework for comparison","year":2017,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; WordNet; Closeness; Semantic similarity; Similarity (geometry); Strengths and weaknesses; Representation (politics); Domain (mathematical analysis); Metric (unit); Data science; Information retrieval; Artificial intelligence; 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":[0.00124264,0.0001366069,0.0003500015,0.00002796532,0.0002600932,0.00007912945,0.002863405,0.00003117141,7.011637e-7],"category_scores_gemma":[0.001270604,0.00006516041,0.0001632491,0.0003164824,0.00007800072,0.0001434472,0.0004515054,0.0002984411,0.00001528406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003778853,"about_ca_system_score_gemma":0.00002820639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002434124,"about_ca_topic_score_gemma":0.00002050413,"domain_scores_codex":[0.9990218,0.00006408245,0.0004012596,0.0001730689,0.0001217837,0.0002179688],"domain_scores_gemma":[0.9969714,0.0006470021,0.0002988218,0.00198006,0.00008037101,0.00002228734],"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":[0.000008327102,0.000154522,0.0005333703,0.004561862,0.0001948595,0.00000244043,0.00240088,0.00400587,0.0003382199,0.2714649,0.004822389,0.7115124],"study_design_scores_gemma":[0.0002707999,0.00006191943,0.005796297,0.02757338,0.0001746956,0.000009746751,0.000009370128,0.5686952,0.003181486,0.08032832,0.3133547,0.0005440623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005141936,0.1036244,0.8928441,0.001749143,0.0002904073,0.0007374853,6.351911e-7,0.0000910705,0.0001485664],"genre_scores_gemma":[0.8454099,0.0496047,0.1024472,0.000164593,0.0001230878,0.000633939,9.667364e-7,0.00007193816,0.001543642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8448957,"threshold_uncertainty_score":0.5320966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02277658548795489,"score_gpt":0.3350866112312231,"score_spread":0.3123100257432682,"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."}}