{"id":"W4389524293","doi":"10.18653/v1/2023.nlposs-1.3","title":"Deepparse : An Extendable, and Fine-Tunable State-Of-The-Art Library for Parsing Multinational Street Addresses","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"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; Open source; Programming language; Natural language processing; Dependency grammar; Top-down parsing; Segmentation; Software","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":[0.0001519482,0.00007402921,0.00008867626,0.00006907275,0.0001166798,0.00009328634,0.0003921168,0.00002153083,0.00001746119],"category_scores_gemma":[0.00004846497,0.00005748315,0.00002781093,0.0002619908,0.0000275543,0.0009644672,0.0002954052,0.00004115396,0.000003394402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004923617,"about_ca_system_score_gemma":0.00007536562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001528303,"about_ca_topic_score_gemma":0.00005560227,"domain_scores_codex":[0.9992024,0.00002709964,0.000169516,0.0002537553,0.0001538184,0.0001934562],"domain_scores_gemma":[0.9993716,0.0001823345,0.00005092755,0.0002978026,0.00004396166,0.00005331231],"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":[0.00003709647,0.0002587085,0.037797,0.0003577075,0.00005681867,0.00001395861,0.002206991,0.05967364,0.002227605,0.2104419,0.05925531,0.6276732],"study_design_scores_gemma":[0.0002769582,0.00003329158,0.007160649,0.00002824636,0.000002632821,0.00000173427,0.00003697948,0.9573005,0.00668755,0.02232625,0.006042382,0.0001027831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3276641,0.00009530082,0.668201,0.001936923,0.000318625,0.0003831042,0.00003618331,0.0003896802,0.0009750333],"genre_scores_gemma":[0.6471005,0.00001393708,0.3463943,0.0002374968,0.00005125454,0.00003412702,0.00002167304,0.00001651382,0.006130158],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8976269,"threshold_uncertainty_score":0.2344095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03731307456453981,"score_gpt":0.2700880737081976,"score_spread":0.2327749991436578,"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."}}