Automatic Extraction of Key Information from Financial Statements Using a Multi-Task Learning Model
Main Article Content
Abstract
Financial statement information extraction and technical document data management both face significant challenges due to complex formats, scattered layouts, and intricate proximity-based semantic relations within semi-structured documents. These challenges are particularly evident in engineering enterprises involving electromagnetic devices, antenna systems, radio-frequency equipment, and related technical service activities, where accurate extraction of financial and operational information is required for reliable reporting and performance analysis. This paper proposes an automatic extraction method based on multi-task learning. The model employs a shared encoder, in which text features and layout features are fused to process four related tasks simultaneously: financial named entity recognition, key-value extraction, entity-value relationship classification, and report item classification with DistilRoBERTa. Experiments based on 500 annual reports show that the accuracy of entity recognition reaches 96.8%, the F1 score of value extraction reaches 88.7%, and the F1 score of relationship classification reaches 91.5%. The model performs particularly well in structured sections such as the balance sheet and income statement. Although its performance declines to some extent in the most complex and unstructured sections of financial statements, such as notes, the overall results demonstrate its effectiveness in improving the accuracy and semantic consistency of financial disclosure information extraction. This study provides a technical reference for intelligent document understanding and reliable data extraction in financial reporting scenarios involving engineering-oriented enterprises and electromagnetic application industries.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
M. Seifzadeh, M. Salehi, B. Abedini, and M. H. Ranjbar, “The relationship between management characteristics and financial statement readability,” EuroMed Journal of Business, vol. 16, no. 1, pp. 108-126, 2021, doi: 10.1108/EMJB-12-2019-0146.
A. A. Olayinka, “Financial statement analysis as a tool for investment decisions and assessment of companies’ performance,” International Journal of Financial. Accounting, and Management, vol. 4, no. 1, pp. 49-66, 2022, doi: 10.35912/ijfam.v4i1.852.
T. K. Kaawaase, C. Nairuba, B. Akankunda, and J. Bananuka, “Corporate governance, internal audit quality and financial reporting quality of financial institutions,” Asian Journal of Accounting Research, vol. 6, no. 3, pp. 348-366, 2021, doi: 10.1108/AJAR-11-2020-0117.
O. Ilori, N. T. Nwosu, and H. N. N. Naiho, “Optimizing Sarbanes-Oxley (SOX) compliance: strategic approaches and best practices for financial integrity: A review,” World Journal of Advanced Research and Reviews, vol. 22, no. 3, pp. 225-235, 2024, doi: 10.30574/wjarr.2024.22.3.1728.
S. Hasnan, M. H. Mohd Razali, and A. R. Mohamed Hussain, “The effect of corporate governance and firm-specific characteristics on the incidence of financial restatement,” Journal of Financial Crime, vol. 28, no. 1, pp. 244-267, 2021, doi: 10.1108/JFC-06-2020-0103.
N. Parmenas, B. Michaela, B. M. Heinrich, and S. Dmitry, “Stock price reactions to publications of financial statements: Evidence from the Moscow Stock Exchange,” Korporativnye financy, vol. 15, no. 1, pp. 19-36, 2021, doi: 10.17323/j.jcfr.2073-0438.15.1.2021.19-36.
A. N. Hasibuan, “The Role of Company Characteristics in the Quality of Financial Reporting in Indonesian,” Jurnal Ilmiah Peuradeun, vol. 10, no. 1, pp. 1-12, 2022, doi: 10.26811/peuradeun.v10i1.666.
C. P. Efunniyi, A. O. Abhulimen, A. N. Obiki-Osafiele, O. S. Osundare, E. E. Agu, and I. A. Adeniran, “Strengthening corporate governance and financial compliance: Enhancing accountability and transparency,” Finance & Accounting Research Journal, vol. 6, no. 8, pp. 1597-1616, 2024, doi: 10.51594/farj.v6i8.1509.
S. Anik, A. Chariri, and J. Isgiyarta, “The effect of intellectual capital and good corporate governance on financial performance and corporate value: A case study in Indonesia,” The Journal of Asian Finance, Economics and Business, vol. 8, no. 4, pp. 391-402, 2021, doi: 10.13106/jafeb.2021.vol8.no4.0391.
M. D. Nastiti and Y. K. Susanto, “Corporate governance, financial ratio and real earnings management in Indonesia stock exchange,” Global Financial Accounting Journal, vol. 6, no. 2, pp. 250-264, 2022, doi: 10.37253/gfa.v6i2.6783.
N. Djamil, “Akuntansi Terintegrasi Islam: Alternatif Model Dalam Penyusunan Laporan Keuangan: Islamic Integrated Accounting: Alternative Models in Preparing Financial Statements,” JAAMTER: Jurnal Audit Akuntansi Manajemen Terintegrasi, vol. 1, no. 1, pp. 1-10, 2023, doi: 10.5281/zenodo.8384951.