{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001615218,0.00100986,0.0008672374,0.002105086,0.0005023376,0.001206379,0.00155161,0.00111887,0.002031516],"category_scores_gemma":[0.005485056,0.000277445,0.001130243,0.001861144,0.0006147212,0.004455459,0.001536867,0.001375977,0.001188684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005057947,"about_ca_system_score_gemma":0.000725791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003447185,"about_ca_topic_score_gemma":0.003487439,"domain_scores_codex":[0.9988441,0.0002371952,0.0001025847,0.0005905481,0.0001472283,0.00007824472],"domain_scores_gemma":[0.9982417,0.0007514096,0.0001819127,0.0005074979,0.0002363199,0.00008109897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005602468,0.0007035318,0.007228755,0.0002182254,0.0002823642,0.0002046666,0.0003838421,0.04204894,0.03318542,0.008661866,0.01341738,0.8931048],"study_design_scores_gemma":[0.00006361033,0.0001680688,0.005669771,0.00002612236,0.000164061,0.0002375949,0.0001382325,0.9370316,0.01720953,0.03413344,0.005104663,0.00005330934],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2453206,0.002467792,0.7362666,0.001291475,0.0006288256,0.0001620145,0.0008945293,0.008006871,0.004961242],"genre_scores_gemma":[0.8100661,0.0007825896,0.1806519,0.0006780927,0.0003000303,0.00007747341,0.003113922,0.0002660604,0.004063949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003447185,"threshold_uncertainty_score":0.00854218,"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."}}