{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002169529,0.0001658358,0.0001998394,0.0005065622,0.0007223385,0.0009816816,0.001467591,0.0000840155,0.000001123059],"category_scores_gemma":[0.00008322146,0.0001381235,0.00004635599,0.0003022689,0.001420002,0.004430947,0.001330728,0.0004079241,0.000002515809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009163424,"about_ca_system_score_gemma":0.0003317761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002044149,"about_ca_topic_score_gemma":0.00002463966,"domain_scores_codex":[0.9984826,0.00001950869,0.0006040672,0.0003298594,0.000380311,0.0001836954],"domain_scores_gemma":[0.9972569,0.0007930013,0.0003818567,0.001152397,0.0003529068,0.00006295186],"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":[0.000002099105,0.000004915487,0.00001632752,0.00008153661,0.00001575935,8.885043e-8,0.01152218,0.002353519,0.000009600029,0.8266149,0.0000210274,0.159358],"study_design_scores_gemma":[0.0001655186,0.00003498229,0.0005917086,0.0002873271,0.00001960516,0.000009635392,0.0002993872,0.8580866,0.000007444138,0.1318497,0.008494596,0.0001534602],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005213566,0.0007152858,0.9846686,0.001670856,0.0005402336,0.0007376974,0.00001374641,0.00004696457,0.01108523],"genre_scores_gemma":[0.7227679,0.0007471069,0.2751643,0.0004006508,0.00004697046,0.00009728907,0.00002707435,0.0000113866,0.0007372989],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8557331,"threshold_uncertainty_score":0.9466379,"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."}}