{"id":"W2905655740","doi":"10.3390/info10010006","title":"A Comparison of Word Embeddings and N-gram Models for DBpedia Type and Invalid Entity Detection","year":2018,"lang":"en","type":"article","venue":"Information","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Entity linking; Information retrieval; Linked data; Word (group theory); Natural language processing; Named-entity recognition; Type (biology); Named entity; Cluster analysis; Artificial intelligence; Knowledge base; Task (project management); Semantic Web; Mathematics; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00607996,0.00249272,0.001354808,0.00412825,0.0009891589,0.003062689,0.00164515,0.001760011,0.002266889],"category_scores_gemma":[0.02820952,0.0006334465,0.001236627,0.003332345,0.000624295,0.008386907,0.00225046,0.002454927,0.002871827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001118482,"about_ca_system_score_gemma":0.00204249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01048917,"about_ca_topic_score_gemma":0.01365475,"domain_scores_codex":[0.9941109,0.00289668,0.000494813,0.0009807358,0.001270842,0.000246083],"domain_scores_gemma":[0.9793761,0.01316779,0.000787647,0.002651179,0.00346305,0.0005542389],"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":[0.002794773,0.001248253,0.01814889,0.001077855,0.001032575,0.0002738325,0.0009734683,0.05754958,0.01161987,0.01079155,0.01576859,0.8787207],"study_design_scores_gemma":[0.00008154292,0.0004410981,0.003616187,0.0001193799,0.00015464,0.0002692576,0.0005964507,0.9691075,0.008360748,0.01097717,0.006157622,0.0001184995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.170174,0.005215295,0.800817,0.001136942,0.0008278907,0.0005432182,0.003629644,0.0102512,0.007404918],"genre_scores_gemma":[0.395995,0.001988079,0.5877478,0.0003512979,0.0002427214,0.0003567951,0.008871814,0.0009536817,0.00349279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01048917,"threshold_uncertainty_score":0.03215426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.036744719496654,"score_gpt":0.3242007531059666,"score_spread":0.2874560336093126,"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."}}