{"id":"W4313021298","doi":"10.23952/jano.4.2022.3.06","title":"Hierarchical reinforcement learning with advantage function for entity relation extraction","year":2022,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Relation (database); Relationship extraction; Reinforcement; Computer science; Function (biology); Extraction (chemistry); Artificial intelligence; Psychology; Data mining; Biology; Chemistry; Social psychology; Chromatography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002744975,0.00006610218,0.0001065423,0.0001425675,0.0003166701,0.0000636604,0.0001198473,0.00002956916,0.00002516322],"category_scores_gemma":[0.00002211815,0.00005497122,0.00003011024,0.0002286596,0.00001887429,0.0004631362,0.00005586747,0.0002349117,3.745522e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007049426,"about_ca_system_score_gemma":0.00002960563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.800998e-7,"about_ca_topic_score_gemma":2.263483e-8,"domain_scores_codex":[0.9992385,0.00002369649,0.0002565156,0.0001293535,0.0002628241,0.00008912381],"domain_scores_gemma":[0.9993435,0.0000661815,0.0004094084,0.00007727532,0.00006738617,0.00003630475],"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":[0.0003853236,0.00004958135,0.0001098903,0.000005716623,0.00001497854,7.551158e-7,0.0001053835,0.9061673,0.0008506998,0.05941372,0.00005868743,0.03283802],"study_design_scores_gemma":[0.001227924,0.001693279,0.0008766841,0.000005483723,0.00003286157,0.00004097984,0.0003891211,0.9754918,0.0005769214,0.005739812,0.01378453,0.00014066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002334873,0.00002439276,0.9961827,0.0006458409,0.0001075733,0.0001542852,2.096874e-7,0.00005851763,0.0004915568],"genre_scores_gemma":[0.8871481,0.00003440005,0.11262,0.00006135368,0.00002916122,0.00002780393,0.000009247099,0.000005012971,0.0000649385],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8848132,"threshold_uncertainty_score":0.2435602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008532871366860002,"score_gpt":0.2314240908626318,"score_spread":0.2228912194957718,"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."}}