{"id":"W4327498768","doi":"10.1007/978-3-031-28241-6_11","title":"Pre-processing Matters! Improved Wikipedia Corpora for Open-Domain Question Answering","year":2023,"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 Waterloo","funders":"","keywords":"Computer science; Question answering; Natural language processing; Information retrieval; Domain (mathematical analysis); Landmark; Artificial intelligence; Text corpus; Open domain; Pipeline (software)","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","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001868737,0.0005658214,0.0006021898,0.0006635051,0.0004168164,0.001859041,0.005564408,0.0003393685,0.000004022626],"category_scores_gemma":[0.0000950247,0.0005618127,0.000119133,0.0005527441,0.0003157875,0.001408526,0.002902152,0.0006342897,0.00001723082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003518869,"about_ca_system_score_gemma":0.0006899587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000728317,"about_ca_topic_score_gemma":0.0001583723,"domain_scores_codex":[0.9956023,0.00003302574,0.0006927297,0.00215174,0.0006855446,0.0008346847],"domain_scores_gemma":[0.9972472,0.0003913833,0.0004814907,0.001417751,0.0002762545,0.0001859079],"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":[0.00001764954,0.00001988054,0.00003909809,0.0001916679,0.00001085118,0.00004481749,0.00166152,0.03129734,0.000953558,0.02666376,0.00004381102,0.939056],"study_design_scores_gemma":[0.0003227223,0.0001028265,0.00004462983,0.0006280005,0.000006204741,0.00002653321,4.073606e-7,0.7557103,0.0003584202,0.2417319,0.0005073099,0.0005607804],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001073849,0.000155267,0.9929759,0.002044998,0.002834715,0.001161642,0.000006897073,0.000388084,0.0003251158],"genre_scores_gemma":[0.02052117,0.00001341853,0.9752003,0.002407809,0.0007713736,0.00007318905,0.00001151538,0.00008482891,0.0009164158],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9384953,"threshold_uncertainty_score":0.9998159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02880047406840642,"score_gpt":0.2781804076201266,"score_spread":0.2493799335517202,"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."}}