A Pluggable Multi-Task Learning Framework for Sentiment-Aware Financial Relation Extraction

TL;DR

This paper introduces a multi-task learning framework that incorporates sentiment analysis into financial relation extraction, improving accuracy by leveraging sentiment cues alongside syntactic information.

Contribution

It proposes a pluggable sentiment-aware module that enhances relation extraction models with sentiment perception, a novel approach for financial domain RE tasks.

Findings

Most models benefit from the auxiliary sentiment task

Enhanced models achieve better relation extraction accuracy

Sentiment information improves understanding of financial relations

Abstract

Relation Extraction (RE) aims to extract semantic relationships in texts from given entity pairs, and has achieved significant improvements. However, in different domains, the RE task can be influenced by various factors. For example, in the financial domain, sentiment can affect RE results, yet this factor has been overlooked by modern RE models. To address this gap, this paper proposes a Sentiment-aware-SDP-Enhanced-Module (SSDP-SEM), a multi-task learning approach for enhancing financial RE. Specifically, SSDP-SEM integrates the RE models with a pluggable auxiliary sentiment perception (ASP) task, enabling the RE models to concurrently navigate their attention weights with the text's sentiment. We first generate detailed sentiment tokens through a sentiment model and insert these tokens into an instance. Then, the ASP task focuses on capturing nuanced sentiment information through predicting the sentiment token positions, combining both sentiment insights and the Shortest Dependency Path (SDP) of syntactic information. Moreover, this work employs a sentiment attention information bottleneck regularization method to regulate the reasoning process. Our experiment integrates this auxiliary task with several prevalent frameworks, and the results demonstrate that most previous models benefit from the auxiliary task, thereby achieving better results. These findings highlight the importance of effectively leveraging sentiment in the financial RE task.