{"id":"W1530262931","doi":"10.1007/11765448_11","title":"Using Semantic Constraints to Improve Question Answering","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Redundancy (engineering); Question answering; Information retrieval; Ranking (information retrieval); Rank (graph theory); Artificial intelligence; Natural language processing; Semantic Web","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":[0.0008249616,0.0004685861,0.0004479137,0.0008123931,0.0002137717,0.0005860598,0.002221829,0.0002661745,0.000007672355],"category_scores_gemma":[0.00007053792,0.0004783415,0.00009543556,0.0004528195,0.0003826905,0.000534081,0.0012023,0.0005860208,0.00002674408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004758052,"about_ca_system_score_gemma":0.0004732124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001357604,"about_ca_topic_score_gemma":0.00006817954,"domain_scores_codex":[0.9962208,0.00002744605,0.000543212,0.001679992,0.0008247939,0.0007038075],"domain_scores_gemma":[0.9979679,0.0001564557,0.0002093312,0.001277584,0.0002037328,0.0001849737],"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":[0.000001381959,0.00001052333,0.00004460579,0.00003718623,0.00000457774,0.00008467513,0.0002750422,0.3855859,0.002516331,0.01352537,0.000004314982,0.59791],"study_design_scores_gemma":[0.0001262357,0.00006059075,0.0000440902,0.0005367053,0.000005819282,0.00008227584,7.536924e-8,0.9515792,0.001996174,0.04485983,0.0001484955,0.0005605144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00063323,0.0001015011,0.99392,0.0003278419,0.002488131,0.0004290064,0.000003032835,0.0001945631,0.001902655],"genre_scores_gemma":[0.3033603,0.000002235397,0.6953108,0.0006908367,0.000476336,0.000003349796,0.000001237936,0.00002567154,0.0001292221],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5973496,"threshold_uncertainty_score":0.9997668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02340020090838834,"score_gpt":0.2666794486687881,"score_spread":0.2432792477603998,"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."}}