{"id":"W4396912844","doi":"10.48550/arxiv.2405.06665","title":"Enhancing Language Models for Financial Relation Extraction with Named Entities and Part-of-Speech","year":2024,"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":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Relation (database); Relationship extraction; Computer science; Natural language processing; Extraction (chemistry); Artificial intelligence; Linguistics; Finance; Business; Data mining; Philosophy; Chemistry","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":[0.002032363,0.001935564,0.0009746747,0.002442901,0.0007124725,0.001877904,0.00180952,0.001315581,0.00463566],"category_scores_gemma":[0.005667503,0.0006295257,0.00207064,0.002114009,0.0004415165,0.005372989,0.0015371,0.002852058,0.009855899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009078718,"about_ca_system_score_gemma":0.001817522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007963016,"about_ca_topic_score_gemma":0.0165292,"domain_scores_codex":[0.998901,0.0003546244,0.00008948813,0.0003616716,0.00019578,0.00009739029],"domain_scores_gemma":[0.9966614,0.002138309,0.000176632,0.0004727427,0.0004610897,0.00008974833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007498834,0.0009434937,0.007772916,0.0007403137,0.0004143697,0.001011067,0.0004929099,0.1274697,0.02559488,0.0129082,0.08815081,0.7337514],"study_design_scores_gemma":[0.00004945509,0.00009583637,0.001339571,0.00006440707,0.0001163039,0.0002862366,0.0001720454,0.9442818,0.01417796,0.01836095,0.02099844,0.00005696113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07251985,0.003595504,0.8600608,0.002345826,0.0007390706,0.0003304879,0.01502057,0.03524661,0.01014135],"genre_scores_gemma":[0.3664724,0.002226431,0.5414477,0.001373098,0.0004663474,0.0005479128,0.07215457,0.001459856,0.0138517],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007963016,"threshold_uncertainty_score":0.01583332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03490882173823154,"score_gpt":0.2106968601577557,"score_spread":0.1757880384195241,"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."}}