{"id":"W2890776849","doi":"10.18653/v1/d18-1517","title":"Similar but not the Same: Word Sense Disambiguation Improves Event Detection via Neural Representation Matching","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Université de Montréal","funders":"","keywords":"Computer science; Word (group theory); Artificial intelligence; Natural language processing; Sentence; Event (particle physics); Matching (statistics); Word-sense disambiguation; SemEval; Representation (politics); Artificial neural network; Task (project management); WordNet; Mathematics","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":[0.0003544723,0.0001026892,0.00007753145,0.00004891415,0.0002913154,0.0002006937,0.0002717271,0.00004199693,0.00001124207],"category_scores_gemma":[0.00005929387,0.0000733114,0.00005264263,0.0001979211,0.00003587278,0.0006220701,0.0001734451,0.0001138989,0.00003501765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005148957,"about_ca_system_score_gemma":0.00001480078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008651531,"about_ca_topic_score_gemma":0.0003333638,"domain_scores_codex":[0.9988067,0.0001148422,0.0002379534,0.000355171,0.000294977,0.0001903784],"domain_scores_gemma":[0.9991006,0.00009759566,0.0001015382,0.0005742552,0.00008687712,0.0000391122],"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":[0.00001534021,0.00001602964,0.00005620075,0.000004771672,0.000009141202,0.000002072275,0.00239735,0.002273861,0.2069267,0.001216668,0.00002689722,0.787055],"study_design_scores_gemma":[0.00011342,0.00003793907,0.005205782,0.000004466373,0.000005265056,0.00001751949,0.0001545551,0.8962312,0.09176751,0.006328497,0.00003946662,0.00009434194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4337494,0.000003931624,0.563507,0.001888291,0.0005172437,0.0001222463,1.449157e-7,0.0001111624,0.0001005762],"genre_scores_gemma":[0.9823201,0.000001802007,0.01600873,0.0009365308,0.0003650217,0.00001385184,9.590045e-7,0.000007365692,0.0003456987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8939574,"threshold_uncertainty_score":0.2989552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02712744165160249,"score_gpt":0.2841262312973287,"score_spread":0.2569987896457262,"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."}}