{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002595467,0.001593707,0.001000299,0.003813266,0.0006763863,0.001226006,0.00207528,0.001843708,0.006370337],"category_scores_gemma":[0.0063278,0.0005101395,0.001459835,0.001985405,0.0009258699,0.003290747,0.001694917,0.001999965,0.003562101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314558,"about_ca_system_score_gemma":0.001647431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00652988,"about_ca_topic_score_gemma":0.01294484,"domain_scores_codex":[0.9982489,0.0007340292,0.0001000244,0.000437621,0.0003898846,0.00008946178],"domain_scores_gemma":[0.9975415,0.001360219,0.0001110474,0.0003406643,0.0004963971,0.0001502035],"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":[0.0007225982,0.0006772149,0.003921236,0.001277992,0.0002522169,0.0004213742,0.0008648863,0.06106513,0.02368318,0.03018309,0.06878456,0.8081465],"study_design_scores_gemma":[0.0001022021,0.0003071088,0.001371916,0.00007186698,0.0001215126,0.0003576119,0.0001570528,0.919463,0.01048691,0.03415315,0.03333945,0.0000680767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01698739,0.002235764,0.9553421,0.0008363626,0.0002046678,0.0005585144,0.002134754,0.01615883,0.005541622],"genre_scores_gemma":[0.3798304,0.001431408,0.5917743,0.0009651212,0.0004654727,0.0006644673,0.01011961,0.0007905537,0.01395876],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00652988,"threshold_uncertainty_score":0.02131093,"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."}}