{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003960041,0.001311461,0.001516113,0.002193713,0.00112691,0.00282219,0.002779825,0.001695765,0.01643073],"category_scores_gemma":[0.02217713,0.000940644,0.001557489,0.002952972,0.0008505856,0.01078535,0.003383174,0.003638696,0.004275021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009474778,"about_ca_system_score_gemma":0.001490213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004457059,"about_ca_topic_score_gemma":0.00667999,"domain_scores_codex":[0.9957343,0.00178327,0.0003250282,0.0007654264,0.001190895,0.0002011047],"domain_scores_gemma":[0.9856296,0.01035949,0.0003518279,0.001579173,0.001796035,0.0002838641],"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":[0.0004384602,0.0004354788,0.001396117,0.001340847,0.0001702893,0.0001700196,0.001151823,0.01830522,0.01865352,0.1053536,0.08772308,0.7648615],"study_design_scores_gemma":[0.000175014,0.0001297303,0.001190335,0.0002546631,0.0002955301,0.0002869385,0.0005256254,0.5427093,0.02258651,0.3183039,0.1134453,0.00009713296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01787236,0.002254316,0.9515891,0.001921926,0.0005749865,0.0002767612,0.002800848,0.009116707,0.01359294],"genre_scores_gemma":[0.1660538,0.001370023,0.8091571,0.0006877706,0.0004791955,0.0004102847,0.01241506,0.001765573,0.007661135],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01643073,"threshold_uncertainty_score":0.05496627,"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."}}