{"id":"W2759162401","doi":"","title":"Named Entity Recognition and Hashtag Decomposition to Improve the Classification of Tweets","year":2016,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec; Université du Québec à Montréal","funders":"","keywords":"WordNet; Computer science; Artificial intelligence; Natural language processing; Preprocessor; Named-entity recognition; Segmentation; Field (mathematics); Task (project management); Information retrieval; Semantics (computer science)","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":[0.0002492807,0.000100657,0.0000952358,0.0001215316,0.00007847357,0.0001049256,0.0004519029,0.00004156939,0.00002452922],"category_scores_gemma":[0.0009002271,0.00007144276,0.00003153022,0.00008501862,0.00005905599,0.00008829712,0.0001223023,0.00007388331,0.00005077939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007058802,"about_ca_system_score_gemma":0.00009294194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001679173,"about_ca_topic_score_gemma":0.00000734106,"domain_scores_codex":[0.9987839,0.00005411564,0.0003157667,0.0003078952,0.0004341367,0.0001041531],"domain_scores_gemma":[0.997813,0.000406328,0.0001810754,0.0001939511,0.001344158,0.00006143817],"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":[0.00003071564,0.0000633549,0.000465759,0.000006718606,0.00002619217,0.000001377192,0.0001991234,0.0005215629,0.004421772,0.8693155,0.0001173198,0.1248306],"study_design_scores_gemma":[0.0005224178,0.0001499444,0.02008489,0.0001658303,0.000009443099,0.000005733115,0.00002482508,0.5916139,0.00146722,0.3845559,0.001207222,0.000192643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.078173,0.000003637228,0.9112883,0.005353692,0.001234085,0.0001769943,0.00008106416,0.00004431335,0.003644927],"genre_scores_gemma":[0.9569142,0.000006566814,0.04241545,0.0003176167,0.0002409534,0.00001760399,0.00002745456,0.000005002535,0.00005511688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8787412,"threshold_uncertainty_score":0.2913351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0829395137147931,"score_gpt":0.3343411440966311,"score_spread":0.251401630381838,"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."}}