{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000558627,0.0004534616,0.0004632283,0.0002814383,0.0001537729,0.0008809564,0.001130316,0.0003640426,0.000002505858],"category_scores_gemma":[0.00009921358,0.0003545766,0.00005143469,0.0005840773,0.00008143391,0.001178969,0.00131721,0.0006739617,0.00000368771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001700446,"about_ca_system_score_gemma":0.0001823949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009381077,"about_ca_topic_score_gemma":0.0003447494,"domain_scores_codex":[0.9973488,0.0001659213,0.0003359791,0.001238996,0.0005395329,0.0003707131],"domain_scores_gemma":[0.9977295,0.0001096365,0.000532124,0.001196453,0.0001999411,0.0002323901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005898611,0.001308363,0.0320864,0.01728142,0.002539163,0.009145135,0.3384838,0.005384322,0.2103896,0.2540896,0.01873355,0.1099688],"study_design_scores_gemma":[0.0007403521,0.0003334086,0.001129147,0.003753376,0.0001412431,0.0001365202,0.001345867,0.4452852,0.2206195,0.3237264,0.00003595806,0.002753038],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4614671,0.002992915,0.5187313,0.001301701,0.0003131006,0.0009848099,0.00003148206,0.0139301,0.0002475121],"genre_scores_gemma":[0.4537095,0.00006376726,0.5451408,0.0003959233,0.00006947857,0.00006406681,0.000042015,0.00004934437,0.0004651383],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4399008,"threshold_uncertainty_score":0.9998906,"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."}}