{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005092022,0.0008450804,0.0009943154,0.001925348,0.0008599857,0.001169585,0.001668328,0.002562668,0.001125891],"category_scores_gemma":[0.02709608,0.0006093163,0.0007330704,0.001393301,0.00162125,0.00496181,0.002131546,0.002138549,0.001031574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006933553,"about_ca_system_score_gemma":0.0006902879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004075131,"about_ca_topic_score_gemma":0.003727567,"domain_scores_codex":[0.9968995,0.001760094,0.0001418302,0.0006124671,0.0004207081,0.0001654505],"domain_scores_gemma":[0.9782643,0.01752463,0.001091069,0.001626055,0.00117166,0.0003222374],"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":[0.002039556,0.0007522073,0.04145701,0.001499382,0.0003087157,0.001669212,0.007572131,0.1451138,0.08908335,0.02389866,0.01331515,0.6732909],"study_design_scores_gemma":[0.00009762061,0.000527877,0.01050575,0.0000952696,0.0001248007,0.0009870449,0.001225126,0.8803239,0.02454962,0.07549525,0.005978154,0.00008954277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4245999,0.002876433,0.5651252,0.001174951,0.00007222747,0.0002106473,0.0009021235,0.002773769,0.002264815],"genre_scores_gemma":[0.8692763,0.0004534091,0.1257957,0.0003934181,0.0001292284,0.0001157722,0.002518716,0.0001677092,0.001149629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005092022,"threshold_uncertainty_score":0.0269295,"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."}}