{"id":"W2602143361","doi":"10.1109/icsc.2017.9","title":"A Context-Aware Approach for the Identification of Complex Words in Natural Language Texts","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Identification (biology); Natural language processing; Artificial intelligence; Context (archaeology); SemEval; Word (group theory); Natural language; Natural language understanding; Natural (archaeology); Word identification; Linguistics; Word recognition; Task (project management)","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":[],"consensus_categories":[],"category_scores_codex":[0.0003366153,0.00004667469,0.00007942002,0.00002799068,0.0001174355,0.0001190789,0.001110413,0.00002114127,0.000003020984],"category_scores_gemma":[0.00006887269,0.00003065767,0.00003311401,0.00003473696,0.00003668269,0.0002130298,0.0001500721,0.00005280533,0.000001353145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001172313,"about_ca_system_score_gemma":0.00001471149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000286942,"about_ca_topic_score_gemma":0.0001803629,"domain_scores_codex":[0.9994442,0.00001502846,0.0001790705,0.000163359,0.0001009494,0.0000973731],"domain_scores_gemma":[0.9990056,0.00006678377,0.0001234006,0.0007542018,0.0000387226,0.00001125885],"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":[0.00001650765,0.0001023846,0.003338281,0.00008495812,0.00002768226,0.000001538234,0.009858879,0.001347157,0.008125801,0.1681131,0.000695739,0.808288],"study_design_scores_gemma":[0.0002191589,0.000003694091,0.01802601,0.000004418784,0.00000143536,9.835675e-7,0.0004003837,0.9799033,0.0009666688,0.0003643062,0.00006805525,0.00004156327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02165466,0.000128358,0.9763595,0.000764971,0.000123281,0.0002671441,0.000001650316,0.0000219721,0.000678412],"genre_scores_gemma":[0.9762114,8.345194e-7,0.0228165,0.00008228709,0.00002691922,0.00002513389,0.000002160072,0.000002418347,0.0008324061],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9785562,"threshold_uncertainty_score":0.2063443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05628516500447647,"score_gpt":0.3162714223898345,"score_spread":0.259986257385358,"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."}}