{"id":"W4401768173","doi":"10.1007/978-3-031-66705-3_14","title":"Investigating a Semantic Similarity Loss Function for the Parallel Training of Abstractive and Extractive Scientific Document Summarizers","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Information retrieval; Similarity (geometry); Function (biology); Natural language processing; Semantic similarity; Artificial intelligence; Biology; Genetics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00445083,0.001006506,0.001084966,0.0007152512,0.0004301381,0.001621647,0.001674938,0.00197817,0.002374387],"category_scores_gemma":[0.008002639,0.000448726,0.0007657362,0.0006957027,0.000428794,0.00307968,0.001362512,0.002128839,0.0009884899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007317366,"about_ca_system_score_gemma":0.001262041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002666546,"about_ca_topic_score_gemma":0.00308133,"domain_scores_codex":[0.9989601,0.0003721734,0.00008766417,0.0002424256,0.0002364614,0.0001011103],"domain_scores_gemma":[0.9961041,0.002487808,0.0001850176,0.0003073901,0.0007783814,0.0001373807],"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":[0.001245754,0.0007418446,0.003391481,0.0002953357,0.0002589884,0.0001404105,0.0001696723,0.2299966,0.034917,0.007391533,0.006310631,0.7151408],"study_design_scores_gemma":[0.00002424038,0.0002103505,0.0004936946,0.000008480537,0.000035507,0.00003194297,0.00003348623,0.9893875,0.007831746,0.001426123,0.0005093493,0.000007575727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.151723,0.001556384,0.8397893,0.0008302472,0.000211028,0.000136151,0.0002113043,0.002412253,0.003130194],"genre_scores_gemma":[0.6789633,0.0005423392,0.3057839,0.0004084041,0.0003102515,0.0001965084,0.00156326,0.0004474815,0.01178461],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00445083,"threshold_uncertainty_score":0.02353853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08608398480217001,"score_gpt":0.314668130721619,"score_spread":0.228584145919449,"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."}}