{"id":"W3152747197","doi":"10.18653/v1/2021.emnlp-main.234","title":"Linguistic Dependencies and Statistical Dependence","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Dependency (UML); Pointwise mutual information; Pointwise; Computer science; Context (archaeology); Natural language processing; ENCODE; Artificial intelligence; Simple (philosophy); Linguistics; Mathematics; Mutual information; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00415345,0.0004757527,0.0006136427,0.002332915,0.001136994,0.00169256,0.000953738,0.001121175,0.005549612],"category_scores_gemma":[0.0467152,0.0006208778,0.0006850646,0.002306164,0.003131602,0.004162072,0.002171518,0.002714469,0.001193465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008119974,"about_ca_system_score_gemma":0.0006676134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00251379,"about_ca_topic_score_gemma":0.00365825,"domain_scores_codex":[0.9960517,0.001548746,0.0002435591,0.001258538,0.0006652073,0.0002322959],"domain_scores_gemma":[0.9482195,0.04031291,0.004312425,0.004259543,0.002130572,0.0007649394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001061146,0.0002889983,0.3667333,0.001168744,0.001109616,0.001496183,0.005972538,0.05847919,0.02531352,0.17418,0.01410685,0.3500899],"study_design_scores_gemma":[0.00004369789,0.0002224504,0.2739777,0.0002455754,0.0003335632,0.002032478,0.00137424,0.1769174,0.006789246,0.5224704,0.01538067,0.0002125792],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6530908,0.002601594,0.3124496,0.002844695,0.00013992,0.00009939467,0.002363202,0.000889124,0.02552169],"genre_scores_gemma":[0.9819409,0.0003767543,0.01472658,0.0002948958,0.0001100636,0.00008272255,0.001106868,0.0001673242,0.00119398],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005549612,"threshold_uncertainty_score":0.0219658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06719722973920086,"score_gpt":0.4482117086445764,"score_spread":0.3810144789053755,"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."}}