{"id":"W2252545675","doi":"10.1007/978-3-319-25252-0_18","title":"Ontology-Based Topic Labeling and Quality Prediction","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Topic model; Reliability (semiconductor); Probabilistic logic; Ontology; Coherence (philosophical gambling strategy); Quality (philosophy); Artificial intelligence; Information retrieval; Natural language processing; Semantics (computer science); Machine learning; Data mining","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":[0.001347574,0.0003751579,0.0005246187,0.0006608307,0.0001699205,0.000243598,0.001638351,0.0003228993,0.000005706054],"category_scores_gemma":[0.0001683717,0.0003491837,0.00007872645,0.0004285385,0.000588898,0.0005480628,0.0007737239,0.0006154898,0.000006037098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003672192,"about_ca_system_score_gemma":0.0004340407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003632082,"about_ca_topic_score_gemma":0.0002251801,"domain_scores_codex":[0.9969046,0.00005448572,0.0005093281,0.001333288,0.0007794779,0.0004187934],"domain_scores_gemma":[0.9977278,0.0003215129,0.0002892579,0.001204766,0.0002966156,0.0001600934],"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":[0.000006502648,0.00002903103,0.0006801331,0.00005166369,0.00001499389,0.000039141,0.0003774437,0.01536853,0.0004725499,0.06340414,0.00002780475,0.9195281],"study_design_scores_gemma":[0.0003425723,0.0002042669,0.0003726566,0.0002433703,0.00001547804,0.00002692183,1.298348e-7,0.5165421,0.001625608,0.4778386,0.002173718,0.0006145755],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001232568,0.0007995791,0.9960902,0.0005780417,0.0004843337,0.0002311537,0.000004848755,0.000362148,0.001326407],"genre_scores_gemma":[0.09015945,0.00003099722,0.908338,0.0009903358,0.0002174709,0.000009939419,0.000006391146,0.00001959593,0.0002278576],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9189135,"threshold_uncertainty_score":0.999896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0454640940380162,"score_gpt":0.31517178953092,"score_spread":0.2697076954929037,"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."}}