{"id":"W3032420555","doi":"","title":"Cooking Up a Neural-based Model for Recipe Classification","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Bank of Canada; Université du Québec à Montréal; Polytechnique Montréal; National Bank of Canada","funders":"","keywords":"Embedding; Computer science; Task (project management); Artificial intelligence; Layer (electronics); Macro; Artificial neural network; Recipe; Natural language processing; Language model; Deep learning; State (computer science); Machine learning; Pattern recognition (psychology); Algorithm; Engineering","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":[0.001903329,0.0009264647,0.0008371901,0.00105586,0.0006376417,0.001745479,0.001489153,0.001941561,0.005485358],"category_scores_gemma":[0.004249679,0.0005598005,0.001100879,0.0008841479,0.000401279,0.002893666,0.0009404281,0.002841444,0.002618741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00146388,"about_ca_system_score_gemma":0.001144451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02049641,"about_ca_topic_score_gemma":0.02676594,"domain_scores_codex":[0.9993526,0.0002077709,0.00004341989,0.0002123417,0.0001048358,0.00007901865],"domain_scores_gemma":[0.9986155,0.0006922549,0.00004197242,0.0001517208,0.0004315446,0.00006698327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009273139,0.0007059289,0.005541811,0.0001926719,0.0004404125,0.0001278318,0.0001687463,0.3341322,0.01472054,0.009172742,0.01608564,0.6177841],"study_design_scores_gemma":[0.00001109235,0.00003962978,0.0003450548,0.000009184121,0.00003728622,0.0000164592,0.00001345786,0.9937894,0.002321947,0.00287026,0.0005350551,0.00001115028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1260491,0.001422477,0.8528692,0.002731309,0.0005428247,0.0002931613,0.001439812,0.00626941,0.0083828],"genre_scores_gemma":[0.8122604,0.000601353,0.1665064,0.0006877583,0.0002814848,0.000284517,0.002469722,0.0003468558,0.01656157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02049641,"threshold_uncertainty_score":0.0407542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1262190574827426,"score_gpt":0.3325542575692801,"score_spread":0.2063352000865376,"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."}}