{"id":"W4362559515","doi":"10.3390/electronics12071692","title":"SS-BERT: A Semantic Information Selecting Approach for Open-Domain Question Answering","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Question answering; Computer science; Open domain; Information retrieval; Labrador Retriever; Domain (mathematical analysis); Precision and recall; Selection (genetic algorithm); Encoder; Dual (grammatical number); Artificial intelligence; Natural language processing; Mathematics; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001041122,0.0001075017,0.0001246642,0.000134398,0.0002349079,0.000401818,0.0007641334,0.00006034234,7.307969e-7],"category_scores_gemma":[0.00008869681,0.0001143882,0.00003742098,0.0006553091,0.00000576521,0.001457365,0.0002573505,0.0001592732,0.00002060576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001559344,"about_ca_system_score_gemma":0.0001622743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001733097,"about_ca_topic_score_gemma":0.00001909104,"domain_scores_codex":[0.9988109,0.00003776902,0.0002415564,0.0002469327,0.0001744117,0.0004883806],"domain_scores_gemma":[0.9994174,0.00005821995,0.00009380307,0.0003176165,0.00007071799,0.0000422251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002735663,0.00005644089,0.0003533753,0.0002656618,0.0000568559,0.000001957329,0.006445964,0.07061961,0.003162675,0.6351681,0.00210576,0.2817362],"study_design_scores_gemma":[0.0003156865,0.00006943945,0.00006162281,0.00001440261,0.000003462159,0.00001164889,0.00005699593,0.9734229,0.00112591,0.01322084,0.01154741,0.0001496371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01631713,0.0001477126,0.9810086,0.0004217614,0.0001951768,0.0005121332,6.182926e-7,0.0003887568,0.001008041],"genre_scores_gemma":[0.6063083,0.00006937459,0.3921945,0.0003444762,0.0001468138,0.0002659574,0.00006890389,0.00002447297,0.0005772673],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9028034,"threshold_uncertainty_score":0.4664617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01930127365845199,"score_gpt":0.2745303152749333,"score_spread":0.2552290416164813,"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."}}