Abstract

In the present day and age, where tremendous amounts of text-based information are produced consistently, keeping ourselves side by side with new data has become troublesome. Reports in the monetary area recount a quantitative story. On the other hand, the subjective or language content that goes with fiscal reports is a fundamental part of the data set utilized by monetary market members for checking and stewardship. This requires the advancement of proficient innovative strategies for utilizing the presence of these monstrous sums of literary information. Perusing monetary reports like yearly reports is incredibly tedious, and consequently, organizations need to distribute valuable human resources to comprehend, examine, and understand these reports. Accordingly, programmed outline strategies can simplify this assignment by empowering admittance to a more modest yet instructive part of the guaranteed record. In this work, a framework using NLP methods for summing up monetary logs in light of questions given by the client is introduced. This framework conquers the difficulties presented by existing segment-based outline models. As AI strategies have been demonstrated to be compelling on downstream errands, for example, text outline. This work aims to exploit these techniques for clear extractive review and create human-like synopses. The proposed model classifies phrases according to their pertinence by utilizing the strength of solo grouping approaches, and it gets a ROUGE-1 score of 46%.

References

1. Abdaljalil, Samir, and Houda Bouamor. 'An exploration of automatic text summarization of financial reports.' In Proceedings of the Third Workshop on Financial Technology and Natural Language Processing, pp. 1-7. 2021
2. El-Haj, M., AbuRa’ed, A., Litvak, M. & Pittaras, N., Giannakopoulos, G. (2020). The Financial Narrative Summarisation Shared Task (FNS 2020).
3. Van Lierde, H., Chow, T. W. S. (2019). Query-oriented text summarization based on hypergraph transversals. Information Processing and Management, 56(4), 1317–1338.
4. Khan, R., Qian, Y., Naeem, S. (2019). Extractive-based text summarization using KMEANS and TF-IDF. International Journal of Information Engineering and Electronic Business, 11(3), 33–44.
5. Araci, D. (2019, August 27). FinBERT: Financial Sentiment Analysis with Pre-trained Language Models.
6. Laskar, M. T. R. (2020, November 14). Utilizing Bidirectional Encoder Representations from Transformers.
7. Hernandez-Castaneda, A., Garcia-Hernandez, R. A., Ledeneva, Y. Millan-Hernandez, C. E. (2020). Extractive Automatic Text Summarization Based on Lexical-Semantic Keywords. IEEE Access, 8, 49896–49907.
8. Yong, S. P., Abidin, A. I. Z., & Chen, Y. Y. (2006). A neural-based text summarization system. Data Mining VII: Data, Text and Web Mining and Their Business Applications.
9. Zheng, S., Lu, A.,& Cardie, C. (2020). SUMSUM@FNS-2020 Shared Task
10. Litvak, Marina, Natalia Vanetik, and Zvi Puchinsky. 'Hierarchical summarization of financial reports with RUNNER.' In Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, pp. 213-225. 2020..
11. Azzi, Abderrahim Ait, and Juyeon Kang. 'Extractive summarization system for annual reports.' In Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, pp. 143-147. 2020.
12. Mingjun Zhao, Shengli Yan, Bang Liu, Xinwang Zhong, Qian Hao, Haolan Chen, Di Niu, Bowei Long, Weidong Guo. QBSUM: a Large-Scale Query-Based Document Summarization Dataset from Real-world Applications
13. Lin, Chin-Yew. 'Rouge: A package for automatic evaluation of summaries.' In Text summarization branches out, pp. 74-81. 2004.
14. Lin, H., Bilmes, J. (2010). Multi-document summarization via budgeted maximization of submodular functions. HLT ’10, Human language technologies: The 2010 annual conference of the north American chapter of the association for computational linguistics. St roudsburg, PA, USA: ACL912–920.
15. Teh, Y. W., Jordan, M. I., Beal, M. J., Blei, D. M. (2004). Sharing clusters among related groups: hierarchical Dirichlet processes. Proceedings of the seventeenth international conference on neural information processing systems, NIP S’04. Cambridge, MA, USA: MIT Press1385–1392.

Download PDF
Back