{"id":"W4404792810","doi":"10.18653/v1/2024.findings-emnlp.653","title":"Make Compound Sentences Simple to Analyze: Learning to Split Sentences for Aspect-based Sentiment Analysis","year":2024,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Computer science; Simple (philosophy); Natural language processing; Artificial intelligence; Sentiment analysis; Compound","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009042734,0.0002922109,0.000508489,0.001353236,0.0003379064,0.001610898,0.0008365931,0.00004920533,0.0003296451],"category_scores_gemma":[0.00004987125,0.0002428696,0.0007807455,0.005055071,0.00002259181,0.0002503662,0.0002641393,0.000115064,0.0002735623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009039987,"about_ca_system_score_gemma":0.00008149572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002909279,"about_ca_topic_score_gemma":0.0004083959,"domain_scores_codex":[0.9969169,0.00009387645,0.0005509219,0.001130861,0.0007322733,0.0005751482],"domain_scores_gemma":[0.9985434,0.0003749969,0.00008636288,0.0005242386,0.0001435032,0.0003275307],"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":[0.00009996822,0.0006433632,0.1631931,0.0002528413,0.01450764,0.0003017033,0.007025301,0.5483857,0.007102836,0.0585807,0.06100518,0.1389016],"study_design_scores_gemma":[0.0001516403,0.000174548,0.002019112,0.00004076861,0.000488615,0.000001337123,0.001036839,0.940289,0.00208447,0.0002330238,0.05307996,0.0004006515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09483102,0.0001986469,0.8962473,0.006660087,0.0004496568,0.0003729429,0.000007636281,0.0003690253,0.00086374],"genre_scores_gemma":[0.9041787,0.000003929791,0.09007853,0.00121052,0.0001415315,0.00006644076,0.00005501373,0.00001609518,0.004249177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8093477,"threshold_uncertainty_score":0.9994255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02397525930705946,"score_gpt":0.3112394222057942,"score_spread":0.2872641628987347,"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."}}