{"id":"W2905137389","doi":"10.1609/aaai.v33i01.33017476","title":"Generating Character Descriptions for Automatic Summarization of Fiction","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Character (mathematics); Computer science; Ranking (information retrieval); Information retrieval; Sample (material); Quality (philosophy); Natural language processing; Artificial intelligence; Mathematics","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":[0.0003800907,0.0001310692,0.0001906482,0.0001297093,0.0001078838,0.0001465076,0.001012415,0.00007936548,0.00002421669],"category_scores_gemma":[0.0003419845,0.00009919285,0.00008760271,0.0004381882,0.00006928171,0.0005795968,0.0001567442,0.0001373838,0.000009580724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003644072,"about_ca_system_score_gemma":0.00006226301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001243019,"about_ca_topic_score_gemma":0.000001753793,"domain_scores_codex":[0.9987916,0.00001051977,0.0004583339,0.0002879767,0.0002737526,0.0001777876],"domain_scores_gemma":[0.9983884,0.00007033646,0.0005027415,0.0002183844,0.0007925307,0.00002768465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009545165,0.00004561058,0.0001459498,0.000107285,0.000005715663,1.646115e-8,0.0005508651,0.00004953218,0.4531381,0.4939806,0.00005189332,0.05191493],"study_design_scores_gemma":[0.00001185245,0.00008754427,0.00003303835,0.0001918194,0.000005573595,9.078084e-7,0.00006529764,0.4040733,0.5352324,0.06020992,0.00001290786,0.00007540253],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2774019,0.00004516186,0.7185261,0.0011799,0.000571569,0.001005662,0.000007538299,0.0002393816,0.001022832],"genre_scores_gemma":[0.866289,0.000005551945,0.1334014,0.00008190286,0.00003436952,0.00003552717,0.000001319211,0.00000811232,0.000142911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.588887,"threshold_uncertainty_score":0.4044967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0536322909089638,"score_gpt":0.2952677741446866,"score_spread":0.2416354832357228,"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."}}