{"id":"W4254133819","doi":"10.1145/564437.564448","title":"The impact of corpus size on question answering performance","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Terabyte; Question answering; Computer science; Information retrieval; Natural language processing; World Wide 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":[0.01755948,0.001352859,0.002231482,0.002440566,0.00211493,0.004806294,0.002065911,0.002119414,0.005400016],"category_scores_gemma":[0.1470115,0.001322435,0.0008904939,0.003647316,0.001684769,0.009566499,0.003288413,0.001925055,0.003370109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001198404,"about_ca_system_score_gemma":0.001992126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006428584,"about_ca_topic_score_gemma":0.006373196,"domain_scores_codex":[0.9827697,0.00837652,0.00234121,0.002779764,0.003072643,0.0006601609],"domain_scores_gemma":[0.8419714,0.1328305,0.001977052,0.00995807,0.0112911,0.001971887],"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":[0.01643308,0.003306307,0.05216685,0.005376299,0.00130101,0.001916591,0.005151569,0.06051697,0.157773,0.004514512,0.1022846,0.5892593],"study_design_scores_gemma":[0.003510718,0.01235446,0.08523628,0.0008005277,0.003040988,0.005225005,0.005612501,0.493927,0.291752,0.01756523,0.08010968,0.0008655268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9261341,0.01024532,0.0232335,0.004227948,0.001307887,0.0005897162,0.005999602,0.01384763,0.01441424],"genre_scores_gemma":[0.9331704,0.003064647,0.03370831,0.001018557,0.0007832691,0.0009373673,0.01876696,0.002714447,0.005836045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01755948,"threshold_uncertainty_score":0.09286451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06702928582532092,"score_gpt":0.3316985989911562,"score_spread":0.2646693131658353,"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."}}