{"id":"W2966132766","doi":"10.1609/aaai.v33i01.33019987","title":"A Multi-Task Learning Framework for Abstractive Text Summarization","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Syntax; Natural language processing; Categorization; Task (project management); Artificial intelligence; Encoder","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000447634,0.0001825834,0.0002212069,0.0001000119,0.0001697101,0.0002421503,0.001430665,0.0001307903,0.00003729186],"category_scores_gemma":[0.0009030392,0.0001475363,0.000113939,0.0003732543,0.00007558598,0.0004800978,0.0002581698,0.0004054276,0.000117654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004878836,"about_ca_system_score_gemma":0.0000820943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002401584,"about_ca_topic_score_gemma":0.000003122487,"domain_scores_codex":[0.998368,0.00001320926,0.0004272564,0.0005368814,0.0003432652,0.0003113747],"domain_scores_gemma":[0.998358,0.0002483226,0.000427295,0.0002729928,0.0006349151,0.00005847799],"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":[0.00003510009,0.00007568445,0.0006786372,0.00004337162,0.00001152841,6.223606e-8,0.001760293,0.001475695,0.0424168,0.8988907,0.00000781784,0.05460436],"study_design_scores_gemma":[0.00003451931,0.0001438529,0.000283874,0.0002364791,0.000007100905,9.833836e-7,0.0006524849,0.628559,0.1719791,0.1977978,0.0001165601,0.0001881975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09707777,0.00001083769,0.8979569,0.001384796,0.0005479711,0.0007176317,0.000002243971,0.00009891843,0.002202922],"genre_scores_gemma":[0.9123678,0.000009692471,0.08699062,0.0001181149,0.00005784009,0.00003649307,5.200951e-7,0.00001279338,0.0004061461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.81529,"threshold_uncertainty_score":0.6016357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08044737931383913,"score_gpt":0.3149212308923305,"score_spread":0.2344738515784914,"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."}}