{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003159865,0.0001615788,0.0002007499,0.00006344691,0.0002147227,0.0002451444,0.0006645521,0.00007111092,0.00001614027],"category_scores_gemma":[0.000106243,0.0001322373,0.00009345069,0.0002566074,0.00007396936,0.0003665197,0.0001394373,0.0001708568,0.000003190488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006246805,"about_ca_system_score_gemma":0.0001011753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572672,"about_ca_topic_score_gemma":0.00001702638,"domain_scores_codex":[0.9985968,0.000008770118,0.0003568263,0.0004606801,0.0002812241,0.0002956343],"domain_scores_gemma":[0.9992548,0.00006515359,0.0001123368,0.0002035671,0.0002940441,0.00007010682],"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":[0.00001924734,0.00003389087,0.00002918288,0.00008476495,0.00001536737,5.709763e-7,0.003365949,0.000697986,0.03404621,0.9244113,0.00001139541,0.03728416],"study_design_scores_gemma":[0.00003266312,0.0000397748,0.000001069815,0.0001336628,0.00001015883,0.000004423679,0.003967937,0.6312702,0.2204279,0.1439806,0.000009824511,0.0001217708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0594367,0.00006915782,0.9341389,0.003630403,0.0002110502,0.0002718931,0.000004524195,0.00005541185,0.002181943],"genre_scores_gemma":[0.9860945,0.00003889509,0.01347389,0.0001820209,0.00005239771,0.00001989488,5.367544e-7,0.00001044398,0.0001274121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9266578,"threshold_uncertainty_score":0.5392481,"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."}}