Research on Extraction Method of Financial Knowledge Based on How Net

Author:

Geng Chaoyang1,Zhao JieJie1,Liu Peng1,Yang Dan1

Affiliation:

1. School of Computer Science and Engineering, Xi’an Technological University , Xi’an , , China

Abstract

Abstract In order to obtain the knowledge information of financial texts more efficiently and make the extracted information such as entity relation attribute more accurate, this paper studies the grammatical features of financial news texts and the semantic features of How Net, and puts forward the scheme of financial information extraction based on How Net. First, the phrase matching is carried out in the dictionary. Then the neural network is used for weighting, BiLSTM is used for character vector feature enhancement training, and then conditional random field (CRF) is used to complete named entity recognition, and then the relationship extraction of entity pairs from the dependency syntax is carried out to complete the research on the construction method of knowledge extraction of text in the financial field. The experimental results show that this model is superior to the other three models in entity recognition, and the overall performance is improved by about 1.2%. In relation extraction, the accuracy and recall rate of the model algorithm adopted in this paper are improved by 5% and 1.5% respectively, which shows that the improvement of the algorithm is effective.

Publisher

Walter de Gruyter GmbH

Subject

General Earth and Planetary Sciences,General Environmental Science

Reference9 articles.

1. Wang Ning, GE Ruifang, Yuan Chunfa, Huang Jinhui, LI Wenjie. Recognition of company names in Chinese Financial News., 2002(02):1–6.

2. Wang S, Xu R, Liu B, et al. Financial named entity recognition based on conditional random fields and information entropy[C]//2014 International Conference on Machine Learning and Cybernetics. Lanzhou: IEEE, 2014: 838-843.

3. Qian-yu li. Financial entity oriented knowledge map construction research [D]. Yunnan university of finance and economics, 2020, DOI: 10.27455 /, dc nki. Gycmc. 2020.000492.

4. Wang Guoming. Based on the deep study of the financial sector knowledge map construction research [D]. The northeast normal university, 2021. The DOI: 10.27011 /, dc nki. Gdbsu. 2021.000237.

5. He Yunqi, Liu Suwen, Qian Longhua, et al. Disease Name Recognition Based on Syntactic and Semantic features [J]. Science China Information Science, 2018, 48 (11): 1546-1557.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3