{"id":"W4306317500","doi":"10.1145/3511808.3557588","title":"Early Stage Sparse Retrieval with Entity Linking","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Question answering; Boosting (machine learning); Artificial intelligence; Task (project management); Ranking (information retrieval); Natural language processing","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":[],"consensus_categories":[],"category_scores_codex":[0.0006818871,0.0001680896,0.0001380614,0.0003539641,0.0003102029,0.0004615068,0.003526133,0.00002917313,0.0001622179],"category_scores_gemma":[0.00008730443,0.0001379285,0.00007415767,0.0004739563,0.00004706587,0.00161678,0.003126065,0.0003082911,0.0001009618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002741003,"about_ca_system_score_gemma":0.00005727194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001345675,"about_ca_topic_score_gemma":0.000005901006,"domain_scores_codex":[0.997985,0.00001514535,0.0004645174,0.0002522737,0.00107387,0.00020918],"domain_scores_gemma":[0.9982912,0.00002378913,0.0005207448,0.0004327291,0.0006832876,0.00004827232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008296829,0.00008512811,0.00191831,0.0001114822,0.00007647013,2.195836e-7,0.003927718,0.0007649125,0.00007958174,0.9869063,0.0006984813,0.005348364],"study_design_scores_gemma":[0.004907182,0.0005636548,0.02136369,0.001002627,0.000109911,0.00003438133,0.006268426,0.2039757,0.002619704,0.06237598,0.6950938,0.001685038],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.338304,0.00001120761,0.09494594,0.00354737,0.002179806,0.001021537,0.00003144622,0.0002518996,0.5597068],"genre_scores_gemma":[0.9792453,0.00001180918,0.01415969,0.0002268844,0.00005023346,0.00006192575,0.00001319803,0.000007223499,0.006223731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9245304,"threshold_uncertainty_score":0.6552491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05496141773196674,"score_gpt":0.2754014181884152,"score_spread":0.2204400004564485,"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."}}