{"id":"W1662133657","doi":"10.1613/jair.2934","title":"From Frequency to Meaning: Vector Space Models of Semantics","year":2010,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Topic Modeling","field":"Computer Science","cited_by":2883,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Semantics (computer science); Meaning (existential); Computer science; Context (archaeology); Space (punctuation); Perspective (graphical); Artificial intelligence; Programming language; Psychology","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":[0.002809105,0.000881384,0.0009516493,0.004467224,0.0009208026,0.005835699,0.001745973,0.001375013,0.005364779],"category_scores_gemma":[0.01830118,0.0004164711,0.001536391,0.005264552,0.003830201,0.01662653,0.002092414,0.002227633,0.001012651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001844048,"about_ca_system_score_gemma":0.001146197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004393936,"about_ca_topic_score_gemma":0.002805263,"domain_scores_codex":[0.9975967,0.001343091,0.000144313,0.0003509118,0.0004302321,0.0001346202],"domain_scores_gemma":[0.9927769,0.00515273,0.0005381376,0.000708864,0.0006210369,0.0002022805],"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":[0.00006323949,0.00002575797,0.00116662,0.00009833342,0.0000396696,0.00004851053,0.0009852167,0.01037541,0.0001736005,0.9436175,0.002276377,0.04112974],"study_design_scores_gemma":[0.000007608036,0.00001382483,0.0001985163,0.00002451734,0.000008953666,0.00004504293,0.0001498627,0.0341371,0.00004400995,0.9621933,0.00316759,0.000009558034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03187528,0.005143562,0.9355267,0.00529764,0.0002537654,0.0001121285,0.001066633,0.0004744394,0.02024987],"genre_scores_gemma":[0.7229849,0.005405884,0.258254,0.0008200248,0.00104879,0.0005380917,0.001479601,0.0002399448,0.009228783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005835699,"threshold_uncertainty_score":0.01794696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2081680926678031,"score_gpt":0.4142808458992752,"score_spread":0.2061127532314721,"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."}}