{"id":"W4285171765","doi":"10.18653/v1/2022.acl-long.360","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Topic Modeling","field":"Computer Science","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automatic summarization; Computer science; Encoder; Transformer; Focus (optics); Artificial intelligence; Pyramid (geometry); Sentence; Multi-document summarization; Training set; Natural language processing; Information retrieval; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001181203,0.001855955,0.001043405,0.001183941,0.0005795963,0.001088194,0.002580562,0.001468767,0.008744086],"category_scores_gemma":[0.003714576,0.000768472,0.001154431,0.001179063,0.0004958499,0.002690153,0.001786848,0.003037051,0.008520286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007308609,"about_ca_system_score_gemma":0.001834303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004233388,"about_ca_topic_score_gemma":0.0107577,"domain_scores_codex":[0.9993159,0.0001745948,0.00004673267,0.0002501003,0.0001390305,0.00007376316],"domain_scores_gemma":[0.9985575,0.0005758504,0.00009201527,0.0002900863,0.0003944433,0.00009000177],"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":[0.0004095273,0.0002931023,0.0008091203,0.0005113073,0.0001894103,0.0002022841,0.0003713688,0.0450198,0.04758563,0.004382497,0.05016866,0.8500573],"study_design_scores_gemma":[0.00007767155,0.0004477834,0.0008359156,0.00005892121,0.0001125717,0.0002035712,0.0001419581,0.9119964,0.04634719,0.01277164,0.02694527,0.00006107013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006450043,0.0007215432,0.9653701,0.0002290499,0.0002426227,0.0002273685,0.00151682,0.02363632,0.001606146],"genre_scores_gemma":[0.1142613,0.0005972545,0.8589962,0.0006278112,0.0002781192,0.0008222105,0.01225881,0.001655773,0.01050256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008744086,"threshold_uncertainty_score":0.02925187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01958442892774115,"score_gpt":0.2617687011148682,"score_spread":0.242184272187127,"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."}}