{"id":"W3166208174","doi":"10.5715/jnlp.28.350","title":"The Effectiveness of Data Augmentation by Removing Unimportant sentence","year":2021,"lang":"en","type":"article","venue":"Journal of Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tokyo Metropolitan University; Institute for Catastrophic Loss Reduction","keywords":"Pointer (user interface); Computer science; Generator (circuit theory); Sentence; Natural language processing; Programming language; Artificial intelligence; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004966058,0.003302474,0.001155328,0.001663545,0.0009108802,0.001803099,0.001718799,0.001722754,0.005175606],"category_scores_gemma":[0.02055384,0.0007330351,0.001589163,0.00125575,0.001243782,0.004438615,0.002108244,0.002938195,0.004023359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010037,"about_ca_system_score_gemma":0.003402674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007422826,"about_ca_topic_score_gemma":0.007638136,"domain_scores_codex":[0.9964521,0.0014896,0.0003367249,0.0009411033,0.0005348835,0.0002455381],"domain_scores_gemma":[0.9840218,0.009916619,0.0005228108,0.003106288,0.001848095,0.0005843085],"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":[0.00455403,0.00197714,0.009931589,0.001345762,0.000426965,0.0004508857,0.0004427402,0.04812123,0.03591022,0.002689919,0.06426332,0.8298863],"study_design_scores_gemma":[0.0008208987,0.002470979,0.01050889,0.0003309722,0.0008337043,0.0007452662,0.0007974905,0.7872038,0.1472121,0.01176678,0.03707308,0.000236039],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6103384,0.01844483,0.2422613,0.007138699,0.007318485,0.001080813,0.02091516,0.06416421,0.02833802],"genre_scores_gemma":[0.7193884,0.002041006,0.234726,0.001739344,0.000733923,0.0007416613,0.0275616,0.001265149,0.01180285],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007422826,"threshold_uncertainty_score":0.02626336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01711823828179371,"score_gpt":0.3082740527003838,"score_spread":0.2911558144185901,"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."}}