{"id":"W4376652178","doi":"10.18653/v1/2023.mwe-1.13","title":"Are Frequent Phrases Directly Retrieved like Idioms? An Investigation with Self-Paced Reading and Language Models","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Hong Kong Polytechnic University; Agence Nationale de la Recherche; Aix-Marseille Université","keywords":"Computer science; Natural language processing; Reading (process); Set (abstract data type); Artificial intelligence; Lexicon; Word (group theory); Reading comprehension; Comprehension; Speech recognition; Linguistics","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":[0.004292924,0.0005276901,0.0006089557,0.0007483488,0.0002337669,0.002055323,0.0007511596,0.0007623992,0.00263844],"category_scores_gemma":[0.04919301,0.0005673917,0.0005522278,0.0007105854,0.0009570455,0.004612457,0.0007869239,0.00111423,0.0005897558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003628882,"about_ca_system_score_gemma":0.0002899623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007603652,"about_ca_topic_score_gemma":0.0005247636,"domain_scores_codex":[0.9980931,0.0008522836,0.0001020628,0.0006035825,0.0002865061,0.00006248551],"domain_scores_gemma":[0.9593071,0.0324648,0.00313858,0.003404853,0.001319595,0.0003651342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003954509,0.001436565,0.1524809,0.001510577,0.000682216,0.001708041,0.02774568,0.03405408,0.4471252,0.02432891,0.002281658,0.3026917],"study_design_scores_gemma":[0.0002797786,0.002156321,0.26216,0.0001051957,0.000375412,0.003224278,0.006217347,0.5304709,0.13637,0.05353059,0.00478356,0.0003266539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9706017,0.0001577644,0.02602337,0.000159247,0.00002362634,0.00006882306,0.0001405579,0.0002769571,0.00254797],"genre_scores_gemma":[0.9857071,0.00008736311,0.0132167,0.00004760439,0.00001476355,0.00003655114,0.0001620644,0.0001158248,0.0006120224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004292924,"threshold_uncertainty_score":0.02270341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03403718456442428,"score_gpt":0.2794349100686895,"score_spread":0.2453977255042653,"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."}}