{"id":"W3200439183","doi":"10.1609/aaai.v36i10.21322","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Key (lock); Natural language processing; Task (project management); Space (punctuation); Artificial intelligence; Masking (illustration); Information extraction; Language model; Semantics (computer science); Information retrieval","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":[0.0003641128,0.0001505697,0.000153132,0.0001173492,0.000319993,0.0003072872,0.0007953014,0.00004654154,0.00002447554],"category_scores_gemma":[0.0001529079,0.0001285146,0.00006041871,0.0001769017,0.00004792508,0.0009946633,0.000339816,0.0002346951,0.000006467182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007329592,"about_ca_system_score_gemma":0.00005053663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001297252,"about_ca_topic_score_gemma":0.000006730746,"domain_scores_codex":[0.9986187,0.00001318507,0.0003998839,0.0003227106,0.0004281529,0.0002173998],"domain_scores_gemma":[0.9991665,0.0000812473,0.0003216632,0.0002109635,0.0001735385,0.00004606169],"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":[0.0003069434,0.0001487871,0.0001193418,0.0000587096,0.00002657878,2.708283e-7,0.02966188,0.01430446,0.08068644,0.480301,0.000168905,0.3942167],"study_design_scores_gemma":[0.00005645146,0.0001210105,0.00005909713,0.00005781613,0.000008456453,0.000001383396,0.0009679131,0.8311893,0.07712787,0.09019998,0.00007687294,0.0001338685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6217225,0.000008238228,0.3737168,0.002648577,0.0002304261,0.0004991308,0.00002392026,0.00006188813,0.001088554],"genre_scores_gemma":[0.9830235,0.000002857895,0.01608798,0.0006427432,0.00005031477,0.00008991681,0.000002831857,0.000007484376,0.00009233734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8168848,"threshold_uncertainty_score":0.5240674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0484413630078671,"score_gpt":0.3015157536877635,"score_spread":0.2530743906798963,"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."}}