Detecting ESG topics using domain-specific language models and data augmentation approaches
This work addresses data scarcity and domain adaptation issues for financial NLP applications, but it is incremental as it applies existing methods to a specific domain.
The paper tackled the challenge of limited labeled data and domain mismatch in financial NLP by using domain-specific pre-training and data augmentation, achieving improved accuracy in ESG controversy classification tasks.
Despite recent advances in deep learning-based language modelling, many natural language processing (NLP) tasks in the financial domain remain challenging due to the paucity of appropriately labelled data. Other issues that can limit task performance are differences in word distribution between the general corpora - typically used to pre-train language models - and financial corpora, which often exhibit specialized language and symbology. Here, we investigate two approaches that may help to mitigate these issues. Firstly, we experiment with further language model pre-training using large amounts of in-domain data from business and financial news. We then apply augmentation approaches to increase the size of our dataset for model fine-tuning. We report our findings on an Environmental, Social and Governance (ESG) controversies dataset and demonstrate that both approaches are beneficial to accuracy in classification tasks.