{"id":"W2965022010","doi":"10.1109/tvcg.2019.2934654","title":"Semantic Concept Spaces: Guided Topic Model Refinement using Word-Embedding Projections","year":2019,"lang":"en","type":"preprint","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Word embedding; Process (computing); Embedding; Semantics (computer science); Space (punctuation); Domain (mathematical analysis); Word (group theory); Point (geometry); Artificial intelligence; Human–computer interaction; Natural language processing; Information retrieval; Programming language","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":[0.0002780313,0.0004443853,0.0005086391,0.0009204169,0.0005142756,0.0008235658,0.0004900122,0.0003524584,0.00001167122],"category_scores_gemma":[0.00000325413,0.0004568073,0.0002788923,0.001059948,0.00006613415,0.0003890051,0.00004912559,0.0004708581,0.000003986815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001112553,"about_ca_system_score_gemma":0.0002335849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001182319,"about_ca_topic_score_gemma":0.00005049323,"domain_scores_codex":[0.9972383,0.0002039381,0.000696482,0.001013646,0.0005351639,0.000312515],"domain_scores_gemma":[0.9982638,0.0000597035,0.0003558832,0.0008384574,0.0003572913,0.0001247993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003840268,0.0001722875,0.00004669717,0.0001271869,0.0001640868,0.000001695077,0.001399281,0.8985546,0.00001666102,0.09688517,0.0001918295,0.002436621],"study_design_scores_gemma":[0.0003926547,0.00006327157,0.00002138573,0.0002816206,0.0001518354,0.000009519266,0.00003455193,0.9968137,0.0002531979,0.001337739,0.0001682371,0.0004722896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007282126,0.00008452315,0.9899257,0.0001064696,0.001645,0.0006032269,0.00001879677,0.0002891055,0.00004506037],"genre_scores_gemma":[0.9746456,0.0005596993,0.02311096,0.0009974365,0.0001332548,0.0000526387,0.00006218359,0.00004967077,0.0003885979],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9673634,"threshold_uncertainty_score":0.9997883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05640038574875286,"score_gpt":0.3296264073778721,"score_spread":0.2732260216291192,"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."}}