Mitigating Negative Transfer with Task Awareness for Sexism, Hate Speech, and Toxic Language Detection

TL;DR

This paper introduces a task-aware multi-task learning approach to reduce negative transfer in detecting sexism, hate speech, and toxic language, achieving state-of-the-art results on benchmark datasets.

Contribution

It presents a novel task awareness method within multi-task learning to mitigate negative transfer and improve performance in offensive language detection tasks.

Findings

Reduced negative transfer in multi-task learning models.

Achieved state-of-the-art performance on EXIST-2021 and HatEval-2019 benchmarks.

Improved detection accuracy for sexism, hate speech, and toxic language.

Abstract

This paper proposes a novelty approach to mitigate the negative transfer problem. In the field of machine learning, the common strategy is to apply the Single-Task Learning approach in order to train a supervised model to solve a specific task. Training a robust model requires a lot of data and a significant amount of computational resources, making this solution unfeasible in cases where data are unavailable or expensive to gather. Therefore another solution, based on the sharing of information between tasks, has been developed: Multi-Task Learning (MTL). Despite the recent developments regarding MTL, the problem of negative transfer has still to be solved. Negative transfer is a phenomenon that occurs when noisy information is shared between tasks, resulting in a drop in performance. This paper proposes a new approach to mitigate the negative transfer problem based on the task awareness concept. The proposed approach results in diminishing the negative transfer together with an improvement of performance over classic MTL solution. Moreover, the proposed approach has been implemented in two unified architectures to detect Sexism, Hate Speech, and Toxic Language in text comments. The proposed architectures set a new state-of-the-art both in EXIST-2021 and HatEval-2019 benchmarks.