{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002045733,0.00003947832,0.00006430038,0.0001072689,0.00004782083,0.00008982552,0.00008991841,0.0000346044,6.980557e-7],"category_scores_gemma":[0.0002777279,0.00003937936,0.000006965661,0.0001968212,0.00002885043,0.00154389,0.00006901688,0.00003918602,0.000003746457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001543145,"about_ca_system_score_gemma":0.0000152363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002098448,"about_ca_topic_score_gemma":0.000006551285,"domain_scores_codex":[0.9996068,0.000005393103,0.0001345957,0.00005476379,0.0001151962,0.00008320081],"domain_scores_gemma":[0.9994848,0.0001028612,0.00005292446,0.00009814064,0.0002313744,0.00002992787],"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":[0.00007216987,0.00002831134,0.01143381,0.0003773381,0.0000213315,6.670748e-8,0.02157684,0.001638876,0.001773487,0.005975319,0.0006646385,0.9564378],"study_design_scores_gemma":[0.0001815777,0.0001774618,0.009815536,0.00001321218,0.000002218147,0.000002069417,0.00003279852,0.9769934,0.01015862,0.001356722,0.001210473,0.00005584641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.439437,0.00001174207,0.5602719,0.00001049801,0.00009166916,0.0000944808,7.044334e-7,0.00004012208,0.00004197418],"genre_scores_gemma":[0.9817873,0.000004684745,0.01816101,0.00001114116,0.00002020106,0.0000078338,0.000002109679,0.000001682756,0.000004041025],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9753546,"threshold_uncertainty_score":0.1605844,"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."}}