{"id":"W3037980084","doi":"10.1109/cist49399.2021.9357170","title":"Leveraging Subword Embeddings for Multinational Address Parsing","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Parsing; Computer science; Python (programming language); Artificial intelligence; Disk formatting; Natural language processing; Artificial neural network; Machine learning; Programming language","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":[0.001044108,0.002688469,0.0009793582,0.002186654,0.000653435,0.002058721,0.001852358,0.002035949,0.007523328],"category_scores_gemma":[0.005327415,0.0007173602,0.001497754,0.002177925,0.000511897,0.007478234,0.002615977,0.00272067,0.01115752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008010234,"about_ca_system_score_gemma":0.00112857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005362459,"about_ca_topic_score_gemma":0.009224807,"domain_scores_codex":[0.998637,0.000342388,0.0001260261,0.0005404251,0.0002037576,0.0001503263],"domain_scores_gemma":[0.9980253,0.0006226709,0.0001442665,0.0006801304,0.0004575543,0.00007002937],"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":[0.0003429983,0.0004926946,0.006597823,0.0003623672,0.0002406944,0.0006583222,0.0005122029,0.07101977,0.015787,0.008411117,0.05082572,0.8447494],"study_design_scores_gemma":[0.00003158687,0.0001136045,0.001397422,0.00006236541,0.00009131731,0.0002617539,0.0003152799,0.9257835,0.02564078,0.0212647,0.02497255,0.00006494235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1713217,0.00167469,0.6815605,0.001154183,0.001215583,0.0003367769,0.009345814,0.1162457,0.01714508],"genre_scores_gemma":[0.4909739,0.0006623401,0.4427766,0.0007349933,0.0002162189,0.0003160287,0.04301855,0.003783135,0.01751808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007523328,"threshold_uncertainty_score":0.02516806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09820144419307504,"score_gpt":0.3210443635176114,"score_spread":0.2228429193245364,"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."}}