{"id":"W3112776819","doi":"10.1609/aaai.v35i14.17485","title":"Segatron: Segment-Aware Transformer for Language Modeling and Understanding","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Peng Cheng Laboratory","keywords":"Computer science; Transformer; Language model; Security token; Perplexity; Sentence; Artificial intelligence; Natural language processing; Speech recognition; Voltage; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009042917,0.002404667,0.0007025368,0.001524547,0.0005266982,0.001442368,0.002581141,0.001096312,0.01598046],"category_scores_gemma":[0.0032292,0.0009990685,0.002103468,0.001106115,0.0005420442,0.004281425,0.001877125,0.002759328,0.01112459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001313056,"about_ca_system_score_gemma":0.001986592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01117512,"about_ca_topic_score_gemma":0.02626097,"domain_scores_codex":[0.9994416,0.0001249534,0.00004083792,0.0002506719,0.00008560112,0.00005634348],"domain_scores_gemma":[0.9991672,0.0003533068,0.0000426895,0.0002545105,0.0001324684,0.00004986512],"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":[0.0007131696,0.0003016443,0.00319926,0.001048682,0.0003353434,0.0004518137,0.0006482136,0.07660989,0.02882871,0.02104924,0.1664834,0.7003306],"study_design_scores_gemma":[0.00008214024,0.0001256624,0.0005332865,0.00004375685,0.00007350802,0.0002662509,0.0001437446,0.9187769,0.02126065,0.02173981,0.03689483,0.00005940657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01476563,0.0005723407,0.7880742,0.0003527157,0.000237621,0.0002865196,0.01274676,0.1784656,0.004498583],"genre_scores_gemma":[0.2134839,0.0008347355,0.6855058,0.0005805014,0.00009818526,0.0008086819,0.07348143,0.01036153,0.01484518],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01598046,"threshold_uncertainty_score":0.05345994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1403263926328943,"score_gpt":0.3085522784521988,"score_spread":0.1682258858193045,"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."}}