Ahead of the Text: Leveraging Entity Preposition for Financial Relation Extraction

TL;DR

This paper presents a top-performing method for financial relation extraction that combines entity insertion, transformer-based classification, and post-processing, achieving first place in a competitive benchmark.

Contribution

The paper introduces a multi-step approach leveraging entity preposition and fine-tuned RoBERTa-large for improved financial relation extraction performance.

Findings

Achieved 1st place in ACM KDF-SIGIR 2023 competition.

Effective combination of entity insertion, transformer fine-tuning, and post-processing.

Outperformed existing methods on the REFind dataset.

Abstract

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.