arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.14960cs.IR
收藏

基于多粒度文本分析的金融文档内容要求溯源

Tracing Content Requirements in Financial Documents using Multi-granularity Text Analysis

Xiaochen Li, Domenico Bianculli, Lionel C. Briand

AI总结:

针对金融文档内容完整性核查效率低的问题,提出结合规则与数据驱动、多粒度分析的FITI框架,实现金融信息类型文本块自动识别,性能优于Transformer基线,可检测约80%缺失信息类型。

摘要:

金融文档的(内容层面的)完整性是投资基金的一项基本要求。为确保完整性,金融监管机构必须投入大量时间,依据相关内容要求仔细核查每一份金融文档,这些内容要求规定了金融文档需包含的信息类型(例如,股票发行条件与流程的说明)。然而,由于金融文档的复杂性,现有技术在帮助监管机构自动识别与金融信息类型相关的文本块方面提供的支持十分有限。\n本文提出了FITI(金融信息类型溯源)框架,通过多粒度文本分析实现金融文档中的内容要求溯源。对于一份新的金融文档,FITI首先筛选出一组候选句子,以实现高效的信息类型识别。随后,为对候选句子进行排序,FITI结合了基于规则和以数据为中心的方法,利用信息检索(IR)和机器学习(ML)技术,分析与某一信息类型相关的词汇、句子及上下文。最后,一个同时考虑句子排序结果和领域特定短语的启发式选择器,会确定与每种信息类型对应的句子列表。\n我们通过评估FITI在100份真实金融文档中溯源金融内容要求的效果,对其进行了验证。实验结果表明,FITI能够实现准确识别,其平均精确率、召回率和F1值分别为0.824、0.646和0.716。FITI的整体性能显著优于最优基线模型(基于Transformer语言模型),F1值高出0.266。此外,FITI可帮助监管机构检测出金融文档中约80%的缺失信息类型。

英文摘要:

The completeness (in terms of content) of financial documents is a fundamental requirement for investment funds. To ensure completeness, financial regulators have to spend significant time carefully checking every financial document based on relevant content requirements, which prescribe the information types to be included in financial documents (e.g., the description of shares' issue conditions and procedures). However, existing techniques provide limited support to help regulators automatically identify the text chunks related to financial information types, due to the complexity of financial documents. In this paper, we propose FITI to trace content requirements in financial documents with multi-granularity text analysis. Given a new financial document, FITI first selects a set of candidate sentences for efficient information type identification. Then, to rank candidate sentences, FITI uses a combination of rule-based and data-centric approaches, by leveraging information retrieval (IR) and machine learning (ML) techniques that analyze the words, sentences, and contexts related to an information type. Finally, a heuristic-based selector, which considers both the sentence ranking and domain-specific phrases, determines a list of sentences corresponding to each information type. We evaluated FITI by assessing its effectiveness in tracing financial content requirements in 100 real-world financial documents. Experimental results show that FITI is able to provide accurate identification with average precision, recall, and F1-score values of 0.824, 0.646, and 0.716, respectively. The overall accuracy of FITI significantly outperforms the best baseline (based on a transformer language model) by 0.266 in terms of F1-score. Furthermore, FITI can help regulators detect about 80% of missing information types in financial documents

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑