{"id":"W151579683","doi":"","title":"Framework for Abstractive Summarization using Text-to-Text Generation","year":2011,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Automatic summarization; Computer science; Text graph; Natural language processing; Sentence; Multi-document summarization; Representation (politics); Domain (mathematical analysis); Information retrieval; Artificial intelligence; Source text; Text generation; Element (criminal law); Mathematics","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":[0.0001491366,0.00009056277,0.00007770364,0.0001009299,0.0001169334,0.0001316822,0.0003730635,0.00009867302,0.00002524634],"category_scores_gemma":[0.0001441724,0.00007909709,0.00002829786,0.0002686039,0.00001087544,0.0006830182,0.00009105323,0.00008249994,0.00001213033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005069797,"about_ca_system_score_gemma":0.00003890331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006297587,"about_ca_topic_score_gemma":0.00001123768,"domain_scores_codex":[0.9993001,0.00001586825,0.0001362444,0.0002739584,0.0001161151,0.0001576743],"domain_scores_gemma":[0.9994142,0.00004676153,0.00007474481,0.0002491339,0.0001656933,0.00004948871],"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":[0.000008939325,0.00004236209,0.00008323044,0.00001065072,0.000007833662,0.000001683074,0.001565893,0.0000274192,0.04292106,0.8728334,0.0004522213,0.08204532],"study_design_scores_gemma":[0.00006710424,0.00008095308,0.0001699558,0.00003348785,0.000006642832,0.000004817178,0.00002118062,0.1151386,0.5807901,0.3032427,0.0002082918,0.000236134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002945797,0.00006583481,0.995366,0.0001541476,0.0001928766,0.0002816247,0.00000114569,0.0003813449,0.0006112198],"genre_scores_gemma":[0.323985,6.774472e-7,0.6754404,0.0004002002,0.00008071456,0.00001594376,0.000002428674,0.000006804459,0.0000678611],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5695906,"threshold_uncertainty_score":0.3225486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08061998104264394,"score_gpt":0.3292945165487601,"score_spread":0.2486745355061161,"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."}}