{"id":"W2166053996","doi":"10.5555/1931390.1931453","title":"Indexing low frequency information for question answering","year":2007,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Question answering; Computer science; Information retrieval; Search engine indexing; Weighting; Clef; Redundancy (engineering); Feature (linguistics); Scheme (mathematics); Document retrieval; Natural language processing; Artificial intelligence; Mathematics; Linguistics","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":[0.007491649,0.0009926411,0.001605335,0.004436781,0.001803906,0.002835169,0.002109875,0.002101403,0.005939309],"category_scores_gemma":[0.03418128,0.000455647,0.001207462,0.004448251,0.0009324379,0.006823787,0.001869557,0.00185734,0.003533827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001818602,"about_ca_system_score_gemma":0.001347469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006269217,"about_ca_topic_score_gemma":0.005652986,"domain_scores_codex":[0.9908172,0.005102196,0.0006629691,0.001144861,0.001948524,0.0003242502],"domain_scores_gemma":[0.974841,0.01975728,0.0005980303,0.002418552,0.0020648,0.0003202962],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001412279,0.001428616,0.004079105,0.001825109,0.0002081047,0.0002144201,0.002232285,0.02492958,0.05867682,0.01628478,0.01593403,0.8727748],"study_design_scores_gemma":[0.0005816713,0.001452755,0.008025819,0.0001763255,0.0003214844,0.000918143,0.001166921,0.8042555,0.07628637,0.06418055,0.0423551,0.0002793577],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.11552,0.00329908,0.8591838,0.001286185,0.0002182287,0.001407782,0.001753003,0.01043368,0.006898233],"genre_scores_gemma":[0.2876793,0.0008260814,0.7028694,0.0003401671,0.0002211745,0.001006939,0.004579408,0.0003424329,0.002135249],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007491649,"threshold_uncertainty_score":0.0396201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01240612294499071,"score_gpt":0.2566936372010145,"score_spread":0.2442875142560238,"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."}}