{"id":"W2964145186","doi":"10.26615/978-954-452-049-6_027","title":"Automatic Identification of AltLexes using Monolingual Parallel Corpora","year":2017,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; WordNet; Leverage (statistics); Artificial intelligence; Parsing; Text simplification; Identification (biology); Task (project management); Natural language; Parallel corpora; Relation (database); Simple (philosophy); Sentence; Machine translation; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0003487689,0.00005830772,0.0001078133,0.0000429597,0.0002243075,0.0002180992,0.000872886,0.0000381892,0.00001312324],"category_scores_gemma":[0.0001241987,0.0000526387,0.00003836868,0.0000487564,0.00007930816,0.0006590664,0.0001177504,0.00003484358,0.00002068712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001675877,"about_ca_system_score_gemma":0.0000582437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001992717,"about_ca_topic_score_gemma":0.00001294919,"domain_scores_codex":[0.9992248,0.00002656972,0.0003048881,0.0001954681,0.0001523397,0.00009594052],"domain_scores_gemma":[0.9982467,0.0000347662,0.0004144141,0.001184295,0.00008795998,0.00003190565],"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":[0.000006306551,0.0002932702,0.01394281,0.0001472238,0.00004096948,0.000002942574,0.003971929,0.001106717,0.1235692,0.5411617,0.0001378559,0.315619],"study_design_scores_gemma":[0.0001067947,0.00001317854,0.1241418,0.0000109085,0.000006799306,0.000004272134,0.00003507553,0.8235589,0.02050737,0.03148712,0.00003825493,0.00008953174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5078298,0.00001296085,0.4914622,0.0001974457,0.00009597941,0.00007794139,6.614925e-7,0.00005574174,0.0002672447],"genre_scores_gemma":[0.9324751,0.000002037896,0.06739137,0.0000135139,0.00001499217,0.000002859231,0.000001007112,0.000002488618,0.00009655205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8224522,"threshold_uncertainty_score":0.2146544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05978571800230753,"score_gpt":0.3233308221855031,"score_spread":0.2635451041831955,"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."}}