Using pre-trained models and graph convolution networks to find the causal relations among events in the Chinese financial text data

Nowadays, information explosion happens in every field. In the stock market of China, automatically understanding the market dynamics is extremely important. However, the information and datasets in Chinese are overwhelming for researchers in the field. How to extract useful information and understand the underlying logic in the Chinese corpus are the research hotspot. Causal relation identification is one of the most central tasks. Many works have made important progress in finding the causal relations in open-domain text, however, there is still space for further explorations in the specific domain of the financial field. In this paper, we propose to use the graph convolution network (GCN) to help represent the dependency relations among the entities in the logical networks provided by the Chinese dependency parsing tool, language technology platform(LTP). The motivation for using the GCN method to help represent the dependency relations is that the causal relations are highly correlated with language structures. Besides, we also choose to use the domain-specific pre-trained model FinBERT because this pre-trained model is specific to the financial field. Results show that the GCN-based method and pertained models of FinBERT in our proposed model play a key role in outperforming the baseline model of the traditional sequential labeling method and the start of art method from F1 of 0.4573 and 0.5506 to 0.6254. Our approach also wins third place in the Eastern District of software service outsourcing competition in China in the year 2021. We believe the proposed methods can contribute as at least an alternative option in future relation extraction tasks.