{"id":"W4389520036","doi":"10.18653/v1/2023.findings-emnlp.82","title":"The Past, Present, and Future of Typological Databases in NLP","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"McGill University","keywords":"Categorical variable; Computer science; Typology; Natural language processing; Variation (astronomy); Rule-based machine translation; Resource (disambiguation); Artificial intelligence; Argument (complex analysis); Computational linguistics; Coding (social sciences); Linguistic typology; Linguistics; Database; Geography; Sociology; Machine learning","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":[0.1462796,0.0007559431,0.002026409,0.01182585,0.008491259,0.03993667,0.007561402,0.009541632,0.006195015],"category_scores_gemma":[0.2022682,0.001723903,0.001190065,0.02581671,0.03690281,0.1045525,0.01388621,0.01150655,0.001280228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01153035,"about_ca_system_score_gemma":0.01032797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007417717,"about_ca_topic_score_gemma":0.00494287,"domain_scores_codex":[0.9130268,0.06049082,0.007045365,0.007060597,0.01024133,0.002135123],"domain_scores_gemma":[0.6326394,0.2773436,0.01235703,0.04897505,0.02350554,0.005179352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000907362,0.00004529083,0.004776035,0.0004680534,0.00002820659,0.0000981052,0.005827958,0.002234266,0.0001701737,0.9055529,0.004582355,0.07612596],"study_design_scores_gemma":[0.00001690369,0.00002091867,0.00135977,0.001518417,0.00001913741,0.0002029381,0.01136167,0.00724873,0.0003415263,0.9125389,0.06528287,0.00008826209],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.06983934,0.07190867,0.4104972,0.376517,0.001932798,0.0002536871,0.001868495,0.0007087616,0.06647407],"genre_scores_gemma":[0.6471552,0.03764024,0.2933514,0.01249947,0.002541014,0.0009623643,0.001708572,0.0005084,0.003633308],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.1462796,"threshold_uncertainty_score":0.7736098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02788861321567965,"score_gpt":0.3134879857757144,"score_spread":0.2855993725600347,"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."}}