{"id":"W2951417328","doi":"10.48550/arxiv.1809.01074","title":"A Novel Neural Sequence Model with Multiple Attentions for Word Sense Disambiguation","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Bridging (networking); Natural language processing; Word (group theory); Sentence; Artificial intelligence; Word-sense disambiguation; Encoder; Sequence (biology); SemEval; Linguistics","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":[0.0009703578,0.0009893993,0.001103742,0.001007121,0.0005834519,0.001079233,0.002771141,0.001851062,0.004598702],"category_scores_gemma":[0.002887995,0.0007450595,0.001055621,0.001356179,0.0008231782,0.002854519,0.001636074,0.002183651,0.00136372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001305347,"about_ca_system_score_gemma":0.001964804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.011702,"about_ca_topic_score_gemma":0.01740402,"domain_scores_codex":[0.9995139,0.000126607,0.00002741843,0.0001907044,0.0000807143,0.00006072587],"domain_scores_gemma":[0.9992304,0.0004242439,0.00006144014,0.00007473183,0.0001465072,0.00006271082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003637995,0.000230894,0.001430678,0.0002127956,0.0001819673,0.000445014,0.0003214919,0.6213439,0.01038934,0.05103102,0.008223366,0.3058258],"study_design_scores_gemma":[0.00001140515,0.00002064352,0.00007199732,0.000007338385,0.00001591585,0.00003673513,0.000007366608,0.9834715,0.000685769,0.01487113,0.0007922671,0.000007903751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02357386,0.00117032,0.9679183,0.001134472,0.0003794853,0.00007201193,0.0003702274,0.001775619,0.003605631],"genre_scores_gemma":[0.6879714,0.001309575,0.2863516,0.001232107,0.0003715128,0.0003394044,0.001050112,0.0004443827,0.02092999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.011702,"threshold_uncertainty_score":0.02326775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1205866417852311,"score_gpt":0.2349481157529617,"score_spread":0.1143614739677306,"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."}}