Multi-task learning (MTL) has emerged as a promising approach for sharing inductive bias across multiple tasks to enable more efficient learning in text classification. However, training all tasks simultaneously often yields degraded performance of each task than learning them independently, since different tasks might conflict with each other. Existing MTL methods for alleviating this issue is to leverage heuristics or gradient-based algorithm to achieve an arbitrary Pareto optimal trade-off among different tasks. In this paper, we present a novel gradient trade-off approach to mitigate the task conflict problem, dubbed GetMTL, which can achieve a specific trade-off among different tasks nearby the main objective of multi-task text classification (MTC), so as to improve the performance of each task simultaneously. The results of extensive experiments on two benchmark datasets back up our theoretical analysis and validate the superiority of our proposed GetMTL.

This paper describes our system used in the SemEval-2023 \textit{Task 10 Explainable Detection of Online Sexism (EDOS)}. Specifically, we participated in subtask B: a 4-class sexism classification task, and subtask C: a more fine-grained (11-class) sexism classification task, where it is necessary to predict the category of sexism. We treat these two subtasks as one multi-label hierarchical text classification problem, and propose an integrated sexism detection model for improving the performance of the sexism detection task. More concretely, we use the pre-trained BERT model to encode the text and class label and a hierarchy-relevant structure encoder is employed to model the relationship between classes of subtasks B and C. Additionally, a self-training strategy is designed to alleviate the imbalanced problem of distribution classes. Extensive experiments on subtasks B and C demonstrate the effectiveness of our proposed approach.

Stance detection aims to identify people’s standpoints expressed in the text towards a target, which can provide powerful information for various downstream tasks. Recent studies have proposed multi-task learning models that introduce sentiment information to boost stance detection. However, they neglect to explore capturing the fine-grained task-specific interaction between stance detection and sentiment tasks, thus degrading performance. To address this issue, this paper proposes a novel multi-task interaction network (MTIN) for improving the performance of stance detection and sentiment analysis tasks simultaneously. Specifically, we construct heterogeneous task-related graphs to automatically identify and adapt the roles that a word plays with respect to a specific task. Also, a multi-task interaction module is designed to capture the word-level interaction between tasks, so as to obtain richer task representations. Extensive experiments on two real-world datasets show that our proposed approach outperforms state-of-the-art methods in both stance detection and sentiment analysis tasks.