{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004666059,0.0005079269,0.0004340754,0.0006342504,0.0002630521,0.0006718716,0.003305504,0.0003581417,0.00002029601],"category_scores_gemma":[0.00007502473,0.000433868,0.0001128714,0.000402005,0.0004183832,0.001476084,0.001809218,0.001098701,0.00005901145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003356506,"about_ca_system_score_gemma":0.0003937851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003982571,"about_ca_topic_score_gemma":0.00003694103,"domain_scores_codex":[0.996372,0.00003763169,0.0004101152,0.001569666,0.001077636,0.0005329216],"domain_scores_gemma":[0.9976184,0.0002349691,0.0004009074,0.001269844,0.0003499528,0.0001259128],"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":[0.000008063289,0.00003083277,0.00004992508,0.0000493943,0.0000083307,0.0001779225,0.0006617549,0.01367073,0.008205753,0.01517141,0.0001083607,0.9618575],"study_design_scores_gemma":[0.0001915159,0.0001348132,0.00006024335,0.0004093786,0.000007230241,0.00009659191,2.125048e-7,0.9116924,0.02036123,0.0660314,0.0002866077,0.0007283736],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002213662,0.001019711,0.9944249,0.0004791238,0.002122918,0.0004337763,0.0000055188,0.0003833161,0.0009093382],"genre_scores_gemma":[0.2892305,0.00003055881,0.7084957,0.001261966,0.0004945603,0.000005013703,0.00001256186,0.00002956175,0.0004395526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9611291,"threshold_uncertainty_score":0.9998113,"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."}}