{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001892847,0.0003569592,0.000639284,0.0001284605,0.000368141,0.0005529243,0.0008518521,0.0004958503,0.0001389382],"category_scores_gemma":[0.01334164,0.0002480139,0.0001308474,0.0005971837,0.0006588843,0.0002455554,0.0009597686,0.001956574,0.000001089508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002309767,"about_ca_system_score_gemma":0.0007049905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009217671,"about_ca_topic_score_gemma":0.0006288913,"domain_scores_codex":[0.9968927,0.0003652138,0.0005656108,0.0007877686,0.0008700239,0.000518674],"domain_scores_gemma":[0.9978799,0.0004925005,0.0004842958,0.0001712188,0.0008284105,0.0001436615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000149063,0.0002362298,0.00712843,0.002092063,0.00007269245,0.00006502424,0.2518945,0.000009264505,0.02132433,0.01874438,0.00009850261,0.6981855],"study_design_scores_gemma":[0.0026278,0.0003799029,0.05597788,0.03053712,0.001220928,0.0001382218,0.6095311,0.05497144,0.06045274,0.1766897,0.001427783,0.006045369],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8854271,0.05347152,0.004001977,0.006066965,0.002364943,0.001720732,0.00005750412,0.0002006584,0.04668859],"genre_scores_gemma":[0.8908983,0.0002990557,0.1077754,0.0002051309,0.0002665179,0.00003345385,0.000006952771,0.0000188002,0.0004963257],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6921402,"threshold_uncertainty_score":0.9999972,"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."}}