{"id":"W6261272","doi":"10.1007/978-3-642-21043-3_9","title":"Using Semantic Information to Answer Complex Questions","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Semantic similarity; Artificial intelligence; Natural language processing; Word (group theory); Graph; String (physics); Benchmark (surveying); Question answering; Subsequence; Information retrieval; Theoretical computer science; Mathematics","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":[0.0005135933,0.0003899501,0.0003681412,0.00116248,0.0002564623,0.0005450756,0.002653376,0.0002206769,0.00002884358],"category_scores_gemma":[0.00006766689,0.0003829561,0.00008480182,0.0005528661,0.0002113187,0.001494327,0.001381372,0.000479386,0.0001327179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003052859,"about_ca_system_score_gemma":0.0007402652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001750535,"about_ca_topic_score_gemma":0.00007532556,"domain_scores_codex":[0.9973366,0.00002341183,0.0005606813,0.0008362539,0.000717559,0.0005254595],"domain_scores_gemma":[0.997744,0.00008602961,0.0002162177,0.001388065,0.0003496186,0.0002160649],"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":[0.000001976893,0.0000154215,0.00003406955,0.0000355065,0.000005535186,0.00001155682,0.00151902,0.09590695,0.0001056032,0.09207682,0.00002483864,0.8102627],"study_design_scores_gemma":[0.00008623031,0.00005975533,0.0001397768,0.0003910711,0.000006461185,0.00007190845,1.465674e-7,0.8636765,0.0001319153,0.1303802,0.00452828,0.0005277182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008815463,0.00006323536,0.9908159,0.0003720845,0.001928018,0.0004215962,0.000003309148,0.0001848556,0.006122834],"genre_scores_gemma":[0.1034198,0.000005786218,0.8925192,0.003652974,0.0002680017,0.000005617955,0.000003563592,0.00001701944,0.0001081228],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.809735,"threshold_uncertainty_score":0.9998623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05982960648080021,"score_gpt":0.2787075651891551,"score_spread":0.2188779587083549,"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."}}