{"id":"W2137006453","doi":"10.1162/coli_a_00206","title":"Towards Topic-to-Question Generation","year":2015,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Predicate (mathematical logic); Natural language processing; Correctness; Artificial intelligence; Topic model; Similarity (geometry); Subsequence; Context (archaeology); String (physics); Information retrieval; Algorithm; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002713166,0.00008291971,0.00008223266,0.00007987137,0.00006386491,0.000125265,0.0003046051,0.00003920281,0.000002441442],"category_scores_gemma":[0.001590768,0.00008868984,0.0000212925,0.0001685498,0.000009745845,0.00005161215,0.0001283754,0.00006717601,0.0001007338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009341155,"about_ca_system_score_gemma":0.0002301341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001741577,"about_ca_topic_score_gemma":0.000002636399,"domain_scores_codex":[0.9990271,0.00003908638,0.0001997272,0.0002462654,0.0003578156,0.0001299462],"domain_scores_gemma":[0.9986648,0.00003707816,0.0000439904,0.0002110077,0.0008798916,0.0001632561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.712155e-7,0.00001301451,0.00009540563,0.000002160425,0.000002493444,0.000004457097,0.0002606621,0.369571,0.000006966484,0.6165475,0.001943664,0.0115518],"study_design_scores_gemma":[0.0001273344,0.00003674771,0.0003845765,0.000005826154,0.000002258746,0.000004102227,0.000003873537,0.8794093,0.00006790484,0.09683399,0.02302152,0.0001025214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00301433,0.00003248185,0.9867741,0.0007762281,0.00247519,0.00008590688,0.000002015397,0.0001454002,0.006694352],"genre_scores_gemma":[0.4886471,2.903229e-7,0.5094382,0.0005696138,0.00122044,0.000003867628,0.00001671601,0.000003841761,0.00009996509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5197135,"threshold_uncertainty_score":0.3616667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08126377489865644,"score_gpt":0.3230650423337741,"score_spread":0.2418012674351177,"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."}}