Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models
This addresses the issue of poor generalization in financial PLMs for financial data analysis, though it is incremental as it builds on existing domain-specific PLM approaches.
The paper tackled the problem of financial pretrained language models (PLMs) underperforming due to insufficiently diverse training data, and showed that training a model (FiLM) on a broader financial corpus outperforms both existing financial and general-domain PLMs, with evidence of generalization to unseen corpus groups.
Over the past few years, various domain-specific pretrained language models (PLMs) have been proposed and have outperformed general-domain PLMs in specialized areas such as biomedical, scientific, and clinical domains. In addition, financial PLMs have been studied because of the high economic impact of financial data analysis. However, we found that financial PLMs were not pretrained on sufficiently diverse financial data. This lack of diverse training data leads to a subpar generalization performance, resulting in general-purpose PLMs, including BERT, often outperforming financial PLMs on many downstream tasks. To address this issue, we collected a broad range of financial corpus and trained the Financial Language Model (FiLM) on these diverse datasets. Our experimental results confirm that FiLM outperforms not only existing financial PLMs but also general domain PLMs. Furthermore, we provide empirical evidence that this improvement can be achieved even for unseen corpus groups.