{"id":"W3022773562","doi":"10.1007/978-3-030-47358-7_35","title":"Query Focused Abstractive Summarization via Incorporating Query Relevance and Transfer Learning with Transformer Models","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Automatic summarization; Transformer; Artificial intelligence; Transfer of learning; Relevance (law); Relevance feedback; Natural language processing; Information retrieval; Image retrieval; Image (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001576566,0.001320937,0.001709715,0.001764824,0.0005112206,0.001605531,0.001754147,0.001187574,0.004820154],"category_scores_gemma":[0.004483495,0.00049842,0.001243485,0.001969889,0.0004601346,0.00369928,0.001522766,0.001768613,0.002985233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006682863,"about_ca_system_score_gemma":0.001047894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002628366,"about_ca_topic_score_gemma":0.004095593,"domain_scores_codex":[0.9989501,0.0002953959,0.0001040631,0.0002805624,0.0002683704,0.0001015631],"domain_scores_gemma":[0.9981825,0.00087519,0.0001294685,0.0002608643,0.0004865541,0.0000654504],"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":[0.0006738356,0.0003043232,0.0005673647,0.0004050517,0.0001864277,0.0001496601,0.0002259351,0.0652157,0.0366252,0.008873969,0.01745749,0.869315],"study_design_scores_gemma":[0.00003889658,0.0001576264,0.0002798831,0.00001314483,0.0001162491,0.00006968756,0.00004548577,0.9770277,0.01027284,0.009005805,0.00294894,0.00002372009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01137697,0.001128122,0.9814799,0.0003113145,0.0001572081,0.0001310782,0.0003377397,0.003632762,0.001444804],"genre_scores_gemma":[0.446851,0.001640345,0.5314206,0.0005618559,0.001008221,0.0003863929,0.00466682,0.0009224133,0.01254224],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004820154,"threshold_uncertainty_score":0.01612508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01735730933643478,"score_gpt":0.212556715224194,"score_spread":0.1951994058877592,"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."}}