{"id":"W4382318308","doi":"10.1609/aaai.v37i13.26963","title":"Transformer-Based Multi-Hop Question Generation (Student Abstract)","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Transformer; Language model; Hop (telecommunications); Sentence; Natural language generation; Question answering; Natural language processing; Artificial intelligence; Task (project management); Text generation; Natural language; Telecommunications; Engineering","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":[0.002074254,0.000854857,0.0007137879,0.00122834,0.0003883694,0.001013485,0.00215361,0.001684327,0.007247573],"category_scores_gemma":[0.006505536,0.0003814855,0.00165282,0.0006985762,0.0006512031,0.002460874,0.001841155,0.001594445,0.002685908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000970203,"about_ca_system_score_gemma":0.0009683351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004208832,"about_ca_topic_score_gemma":0.005842832,"domain_scores_codex":[0.998708,0.0004682455,0.00008364052,0.0004636519,0.0001957705,0.00008065968],"domain_scores_gemma":[0.9971174,0.001758993,0.0001062785,0.0004992652,0.0003930408,0.0001249974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009599385,0.0006520015,0.004238241,0.0008985084,0.0001719883,0.0008828567,0.000829492,0.1607797,0.02351257,0.02567164,0.05283085,0.7285722],"study_design_scores_gemma":[0.00009609888,0.0001377169,0.0004432529,0.0000235769,0.0000451877,0.0002929502,0.00005187138,0.9591606,0.01106882,0.01942694,0.009230082,0.00002292446],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03197757,0.001074939,0.927321,0.0009965403,0.0002751591,0.0007047419,0.002615698,0.03033349,0.004700812],"genre_scores_gemma":[0.4612801,0.0003468306,0.5204542,0.0006826409,0.0001215287,0.000412526,0.008395587,0.0007909678,0.007515592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007247573,"threshold_uncertainty_score":0.0242455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1628441148780427,"score_gpt":0.3500064306314004,"score_spread":0.1871623157533577,"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."}}