{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004513924,0.002180349,0.001140057,0.002994552,0.0008826433,0.00382418,0.002364889,0.001471446,0.005847161],"category_scores_gemma":[0.01841805,0.000848383,0.002187468,0.002416572,0.001470216,0.00754923,0.004612564,0.002401785,0.002185856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008325644,"about_ca_system_score_gemma":0.00146085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002824185,"about_ca_topic_score_gemma":0.003889992,"domain_scores_codex":[0.9959902,0.00176811,0.0002653052,0.001004467,0.0008481941,0.0001236534],"domain_scores_gemma":[0.9916659,0.005180416,0.0006185056,0.001270192,0.001011014,0.0002539608],"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":[0.001023341,0.0005470505,0.003037504,0.001419129,0.0003456238,0.0004782705,0.01536821,0.05561621,0.04571112,0.07831126,0.01771478,0.7804275],"study_design_scores_gemma":[0.0002111169,0.0002386077,0.001083286,0.0001856247,0.00015233,0.0003335223,0.002367209,0.7728875,0.03322464,0.1396629,0.04948359,0.0001696822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00519555,0.0001329623,0.9875316,0.0001456462,0.00002463807,0.0001364265,0.0001987068,0.005958499,0.0006760053],"genre_scores_gemma":[0.08607043,0.0001942733,0.910269,0.00009070071,0.00004874051,0.0004071966,0.000849009,0.0009103452,0.001160428],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005847161,"threshold_uncertainty_score":0.0238722,"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."}}