{"id":"W4289743854","doi":"10.48550/arxiv.1807.10805","title":"Improving Neural Sequence Labelling Using Additional Linguistic Information","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Chunking (psychology); Computer science; Natural language processing; Sequence labeling; Artificial intelligence; Sequence (biology); Named-entity recognition; Word (group theory); Labelling; Sentence; Benchmark (surveying); Categorical variable; Task (project management); Machine learning; 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":[0.001435092,0.0009736379,0.0009859138,0.0009854983,0.0006068109,0.001122636,0.001863418,0.002268557,0.003696272],"category_scores_gemma":[0.006782279,0.0004909535,0.0008550313,0.001044305,0.0006956874,0.004473015,0.00131515,0.002443182,0.002601434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0014528,"about_ca_system_score_gemma":0.001678015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007946831,"about_ca_topic_score_gemma":0.01164921,"domain_scores_codex":[0.9993619,0.0001982376,0.00003965546,0.000230353,0.0001132735,0.00005652703],"domain_scores_gemma":[0.9969547,0.001776817,0.0002030051,0.0004954426,0.0004830062,0.00008704395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003725146,0.000367193,0.001946362,0.0002716688,0.00008691524,0.0001708873,0.0002377165,0.4984493,0.01310451,0.01521779,0.01352148,0.4562538],"study_design_scores_gemma":[0.000008693547,0.00002596859,0.0001201352,0.00001334641,0.00001000467,0.0000207429,0.00001254672,0.9890397,0.002172096,0.007511719,0.001057444,0.000007689505],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06578939,0.00102057,0.9197848,0.0009982954,0.0002722452,0.0001044233,0.0006069838,0.00550466,0.005918595],"genre_scores_gemma":[0.6172082,0.000799751,0.3575279,0.001163246,0.0002065846,0.0002933098,0.005069492,0.0005767171,0.01715486],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007946831,"threshold_uncertainty_score":0.01580113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0713100375631831,"score_gpt":0.2172160888038689,"score_spread":0.1459060512406858,"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."}}