{"id":"W2925631053","doi":"10.1007/978-3-030-15719-7_14","title":"Neural Diverse Abstractive Sentence Compression Generation","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Paraphrase; Sentence; Natural language processing; Machine translation; Artificial intelligence; Encoder; Compression (physics); Speech recognition","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":[0.0004343449,0.0008524704,0.000646552,0.0007870563,0.0004428515,0.000710561,0.001304723,0.001040743,0.01645932],"category_scores_gemma":[0.001590393,0.0003055589,0.0006013116,0.0008478646,0.0003746629,0.001092711,0.001240587,0.001104616,0.004307269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003376896,"about_ca_system_score_gemma":0.0004522057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009335571,"about_ca_topic_score_gemma":0.002296846,"domain_scores_codex":[0.9996715,0.00007700103,0.00002126017,0.00008751377,0.00009795526,0.00004482709],"domain_scores_gemma":[0.9993408,0.0002996963,0.0000239914,0.0001125213,0.0001897316,0.00003315923],"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":[0.0003685642,0.0002008371,0.0003405268,0.0002764899,0.00005030436,0.0004271151,0.0001115851,0.03171087,0.05113641,0.01599903,0.02483701,0.8745413],"study_design_scores_gemma":[0.00008830884,0.0002220639,0.0007302111,0.00004307627,0.000068412,0.000447229,0.00007608974,0.8953415,0.06306935,0.0299631,0.009916576,0.00003421486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08835626,0.001715122,0.8667024,0.000761164,0.000928409,0.0004064186,0.001973486,0.01237274,0.02678402],"genre_scores_gemma":[0.5239674,0.0006132125,0.4366698,0.0005969789,0.0004809568,0.000457017,0.006943713,0.0009359778,0.02933504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01645932,"threshold_uncertainty_score":0.05506188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02282935388186901,"score_gpt":0.2712604724152494,"score_spread":0.2484311185333804,"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."}}