{"id":"W4284673342","doi":"10.1145/3477495.3531793","title":"Detecting Frozen Phrases in Open-Domain Question Answering","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Huawei Technologies","keywords":"Computer science; Natural language processing; Question answering; Open domain; Artificial intelligence; Context (archaeology); Domain (mathematical analysis); Task (project management); Information retrieval; Noun phrase; Natural language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003025074,0.0000915339,0.0001164197,0.0006345502,0.0002519308,0.0004623117,0.002465585,0.00003245238,0.00003215332],"category_scores_gemma":[0.001384607,0.00008051095,0.00001297561,0.0006119409,0.00004318576,0.001699532,0.003440479,0.0004767499,0.000003777488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000368975,"about_ca_system_score_gemma":0.0002782027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000788822,"about_ca_topic_score_gemma":0.00000988231,"domain_scores_codex":[0.9978892,0.00003604622,0.0005013591,0.0002103294,0.001120684,0.0002424004],"domain_scores_gemma":[0.9990437,0.0001810567,0.0001942541,0.000133212,0.0004013777,0.00004642267],"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":[0.0009673361,0.0003124872,0.1489699,0.0001782716,0.00003771424,0.000004124129,0.02851018,0.001385467,0.005192324,0.7257306,0.0002622346,0.08844935],"study_design_scores_gemma":[0.008079863,0.001061183,0.1906354,0.001884245,0.000002283864,0.00008842922,0.03007375,0.3532676,0.1015536,0.2939504,0.0180794,0.00132386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881107,0.000007112105,0.002441148,0.002505004,0.0002478494,0.0004251057,0.000003347584,0.0000203722,0.006239333],"genre_scores_gemma":[0.9822533,0.00001268771,0.01748566,0.0001018497,0.00001135396,0.00006593715,0.000003392251,0.000002903563,0.00006294631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4317802,"threshold_uncertainty_score":0.4581712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09370089461891895,"score_gpt":0.3472013579749158,"score_spread":0.2535004633559969,"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."}}