Distant finetuning with discourse relations for stance classification

TL;DR

This paper introduces a topic-independent stance classification method using discourse relations to automatically generate training data, combined with a multi-stage training framework, leading to state-of-the-art results in a shared task.

Contribution

The paper presents a novel approach that leverages discourse relations for silver label data extraction and a 3-stage training process to improve stance classification performance.

Findings

Achieved top performance in the NLPCC 2021 stance classification shared task.

Demonstrated that discourse relation-based data extraction enhances model accuracy.

Showed that multi-stage training reduces noise and improves stance classification results.

Abstract

Approaches for the stance classification task, an important task for understanding argumentation in debates and detecting fake news, have been relying on models which deal with individual debate topics. In this paper, in order to train a system independent from topics, we propose a new method to extract data with silver labels from raw text to finetune a model for stance classification. The extraction relies on specific discourse relation information, which is shown as a reliable and accurate source for providing stance information. We also propose a 3-stage training framework where the noisy level in the data used for finetuning decreases over different stages going from the most noisy to the least noisy. Detailed experiments show that the automatically annotated dataset as well as the 3-stage training help improve model performance in stance classification. Our approach ranks 1st among 26 competing teams in the stance classification track of the NLPCC 2021 shared task Argumentative Text Understanding for AI Debater, which confirms the effectiveness of our approach.