{"paper_id":"2311.08533","title":"Natural Language Processing for Financial Regulation","authors":["Ixandra Achitouv","Dragos Gorduza","Antoine Jacquier"],"paper_date":"2023-11-14","paper_type":"perspective-policy","paper_url":"https://arxiv.org/pdf/2311.08533v1","page_url":"https://thequant.space/flowcharts/natural-language-processing-for-financial-regulation/","scores":{"empirical_rigor":3,"math_complexity":6,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes an adaptive pre‑training and a fully unsupervised domain‑adaptation method (GPL) to improve semantic matching between financial rules and policies using freely available resources.","quote":"we explore the results of performing an Adaptative Pre-Training method and a purely unsupervised approach, using GPL.","summary":"This article provides an understanding of Natural Language Processing techniques in the framework of financial regulation, more specifically in order to perform semantic matching search between rules and policy when no dataset is available for supervised learning. We outline how to outperform…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A pseudo‑Markovian (k‑gram) approximation is assumed for estimating word probabilities.","type":"model","stated":"explicit","quote":"one usually assumes a pseudo-Markovian approximation (the k-gram model)"},{"assumption":"Pairs are kept only if cosine similarity is above 0.7, an empirical threshold for matching.","type":"data","stated":"implied","quote":"For each model, we keep the rule/policy match sentences if the cosine similarity (6) is above 0.7. This is an empirical choice that provides fair matches."}]},"datasets":{"status":"available","items":[{"name":"FCA Rulebook 2022","provider":"Financial Conduct Authority","kind":"text-news","access":"public","period":null,"universe":null,"quote":"The dataset of rules is publicly available from Financial Conduct Authority (FCA) Rulebook 2022. After cleaning and splitting the rules into sentences of length 200, we obtain about 50,000 sentences, composed of 21,914 rule IDs."},{"name":"FinregE policies","provider":"FinregE","kind":"text-news","access":"commercial","period":null,"universe":null,"quote":"The policies’ dataset was obtained from FinregE and is composed of 2,374 policies that may not cover all of the newly edited FCA"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"All‑MiniLM‑L6‑v2 with Step 1 & 2 improves Score 1 from 0.21 to 0.27 (29% increase) and Score 2 from 0.46 to 0.56 (22% increase).","kind":"performance","quote":"all-MiniLM-L6-v2 + Step 1 & 2 0.27 0.56 Improvement 29% 22%"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":4,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:19:35Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}