Ahead of the Text: Leveraging Entity Preposition for Financial Relation Extraction
This work addresses financial relation extraction for a specific competition, representing an incremental application of existing methods.
The authors tackled the problem of extracting financial entity relations by fine-tuning a transformer model and applying post-processing, achieving first place in the ACM KDF-SIGIR 2023 competition.
In the context of the ACM KDF-SIGIR 2023 competition, we undertook an entity relation task on a dataset of financial entity relations called REFind. Our top-performing solution involved a multi-step approach. Initially, we inserted the provided entities at their corresponding locations within the text. Subsequently, we fine-tuned the transformer-based language model roberta-large for text classification by utilizing a labeled training set to predict the entity relations. Lastly, we implemented a post-processing phase to identify and handle improbable predictions generated by the model. As a result of our methodology, we achieved the 1st place ranking on the competition's public leaderboard.