ABSTRACT
Extracting causality information from unstructured natural language text is a challenging problem in natural language processing. However, there are no mature special causality extraction systems. Most people use basic sequence labeling methods, such as BERT-CRF model, to extract causal elements from unstructured text and the results are usually not well. At the same time, there is a large number of causal event relations in the field of finance. If we can extract enormous financial causality, this information will help us better understand the relationships between financial events and build related event evolutionary graphs in the future. In this paper, we propose a causality extraction method for this question, named CBCP (Center word-based BERT-CRF with Pattern extraction), which can directly extract cause elements and effect elements from unstructured text. Compared to BERT-CRF model, our model incorporates the information of center words as prior conditions and performs better in the performance of entity extraction. Moreover, our method combined with pattern can further improve the effect of extracting causality. Then we evaluate our method and compare it to the basic sequence labeling method. We prove that our method performs better than other basic extraction methods on causality extraction tasks in the finance field. At last, we summarize our work and prospect some future work.
- Z. Li, X. Ding, and T. Liu, “Constructing Narrative Event Evolutionary Graph for Script Event Prediction,” arXiv:1805.05081 [cs], May 2018, Accessed: Jan. 11, 2021. [Online]. Available: http://arxiv.org/abs/1805.05081Google Scholar
- Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” arXiv:1810.04805 [cs], May 2019, Accessed: Jan. 26, 2021. [Online]. Available: http://arxiv.org/abs/1810.04805Google Scholar
- John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling se- quence data. In Proceedings of the Eighteenth International Conference on Machine Learning, ICML ’01, pages 282–289, San Francisco, CA, USA. Mor- gan Kaufmann Publishers Inc.Google Scholar
- Jianlin Su. (Dec.14, 2019). “Based on Conditional Layer Normalization condition of text generation” [Blog post]. Retrieved from https://spaces.ac.cn/archives/7124Google Scholar
- F. Eeckman, “The Sigmoid Nonlinearity in Prepyriform Cortex,” in Neural Information Processing Systems, 1988. Accessed: Jun. 05, 2021. [Online]. Available: https://proceedings.neurips.cc/paper/1987/file/c9f0f895-fb98ab9159f51fd0297e236d-Paper.pdfGoogle Scholar
- A. Vaswani , “Attention Is All You Need,” arXiv:1706.03762 [cs], Dec. 2017, Accessed: Feb. 15, 2021. [Online]. Available: http://arxiv.org/abs/1706.03762Google Scholar
- Y. Cui , “Pre-Training with Whole Word Masking for Chinese BERT,” arXiv:1906.08101 [cs], Oct. 2019, Accessed: Jun. 01, 2021. [Online]. Available: http://arxiv.org/abs/1906.08101Google Scholar
- D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv:1412.6980 [cs], Jan. 2017, Accessed: Apr. 11, 2021. [Online]. Available: http://arxiv.org/abs/1412.6980Google Scholar
- Christopher S. G. Khoo, Syin Chan, and Yun Niu. Extracting causal knowledge from a medical database using graphical patterns. Proceedings of the 38th annual meeting of the association for computational linguistics, pages 336–343, 2000.Google ScholarDigital Library
- Roxana Girju and Dan Moldovan. Text mining for causal relations. Proceedings of the FLAIRS Conference, page 360–364, 2002.Google Scholar
- Tirthankar Dasgupta, Rupsa Saha, Lipika Dey, and Abir Naskar. Automatic Ex- traction of Causal Relations from Text using Linguistically Informed Deep Neural Networks. Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pages 306–316, 2019.Google Scholar
- Oktie Hassanzadeh, Debarun Bhattacharjya, Mark Feblowitz, Kavitha Srinivas, Michael Perrone, Shirin Sohrabi, and Michael Katz. Answering binary causal ques- tions through large-scale text mining: An evaluation using cause-effect pairs from human experts. IJCAI International Joint Conference on Artificial Intelligence, 2019-Augus:5003–5009, 2019.Google Scholar
Recommendations
A Generative Approach for Financial Causality Extraction
WWW '22: Companion Proceedings of the Web Conference 2022Causality represents the foremost relation between events in financial documents such as financial news articles, financial reports. Each financial causality contains a cause span and an effect span. Previous works proposed sequence labeling approaches ...
Building a Corpus for Chinese Causality Extraction in Futures Domain
Chinese Lexical SemanticsAbstractCausality extraction is to extract cause events and effect events from text, which is the basis for constructing causal event graphs and doing causal reasoning. The research on causality extraction needs the support of annotated causality corpus. ...
Financial Causality Extraction Based on Universal Dependencies and Clue Expressions
AbstractThis paper proposes a method to extract financial causal knowledge from bi-lingual text data. Domain-specific causal knowledge plays an important role in human intellectual activities, especially expert decision making. Especially, in the ...
Comments