{"id":"W4285288434","doi":"10.18653/v1/2022.acl-long.233","title":"LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University; Canadian Institute for Advanced Research","funders":"Samsung; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Computer science; Parsing; Generalization; Artificial intelligence; Natural language processing; Inference; Graph; Sequence (biology); Theoretical computer science; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002236741,0.0001805634,0.0003747885,0.0001856624,0.000588534,0.0001052121,0.001333364,0.00008143452,6.294517e-7],"category_scores_gemma":[0.008875417,0.0001461814,0.0002180064,0.0008217794,0.00004237169,0.0001208024,0.0004801235,0.0001571063,1.787047e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003655168,"about_ca_system_score_gemma":0.0001002037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002881517,"about_ca_topic_score_gemma":0.000004963916,"domain_scores_codex":[0.9976212,0.00007037551,0.000796599,0.0003232472,0.0008902467,0.0002983073],"domain_scores_gemma":[0.9952042,0.0007195413,0.001913463,0.0001553389,0.001977406,0.00003007468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000191066,0.0007426006,0.2134751,0.02211463,0.0005532916,8.926239e-7,0.01269919,0.0908847,0.01329786,0.6377997,0.00768197,0.0005590065],"study_design_scores_gemma":[0.002138906,0.0003051359,0.005687237,0.003684714,0.0003864819,0.000009310566,0.0006999211,0.5793487,0.01082989,0.3955388,0.0006101956,0.0007606526],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7488352,0.004274812,0.1833246,0.01994973,0.01396347,0.02339455,0.001752122,0.001728603,0.002776896],"genre_scores_gemma":[0.8884737,7.521963e-7,0.1106484,0.0003584427,0.00009770661,0.0001431931,0.0000150055,0.00002419547,0.0002386513],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4884641,"threshold_uncertainty_score":0.9994733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008235714887199415,"score_gpt":0.2424025283105196,"score_spread":0.2341668134233202,"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."}}