{"id":"W2780329366","doi":"10.1142/s1793351x17400207","title":"On the Influence of Contextual Features for the Identification of Complex Words","year":2017,"lang":"en","type":"article","venue":"International Journal of Semantic Computing","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Medical Research Council Canada","keywords":"Computer science; SemEval; Word (group theory); Artificial intelligence; Natural language processing; Identification (biology); Context (archaeology); Set (abstract data type); Natural language; Word identification; Word recognition; Linguistics; Task (project management)","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":[0.001294438,0.00006631671,0.0001411679,0.00007434851,0.0001953436,0.0001890037,0.002903171,0.00002029814,0.000002108142],"category_scores_gemma":[0.001169288,0.0000391046,0.0001147341,0.00003449611,0.0001086106,0.0002029075,0.0002553865,0.0001332114,5.930925e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002163798,"about_ca_system_score_gemma":0.00005116386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003820529,"about_ca_topic_score_gemma":0.000004628476,"domain_scores_codex":[0.9986306,0.00003698631,0.0006306187,0.00009797922,0.0005194124,0.0000843822],"domain_scores_gemma":[0.9956622,0.001304388,0.001760148,0.0003954433,0.0008612685,0.00001662767],"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":[0.0001113268,0.0001365944,0.00366101,0.00004314116,0.0004829688,0.00001016323,0.005194977,0.2115124,0.03542401,0.6010715,0.0006536975,0.1416982],"study_design_scores_gemma":[0.0006741417,0.00009209811,0.2070374,0.0004806673,0.00002452905,0.0000880823,0.0002697309,0.7656545,0.00649982,0.01895278,0.0001365011,0.00008976164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5334742,0.00003093295,0.4614689,0.00438966,0.000518725,0.00007124531,0.000001440913,0.000002728576,0.00004212731],"genre_scores_gemma":[0.9960669,0.000006220315,0.003568593,0.000155288,0.0001788645,5.970051e-7,1.847138e-7,0.000003261686,0.00002015089],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5821187,"threshold_uncertainty_score":0.5394863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04346768116821662,"score_gpt":0.3322063310706441,"score_spread":0.2887386499024275,"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."}}