Mitigating Negative Transfer with Task Awareness for Sexism, Hate Speech, and Toxic Language Detection
This work addresses a key bottleneck in multi-task learning for natural language processing, specifically for content moderation tasks, though it appears incremental as it builds on existing MTL frameworks.
The paper tackles the negative transfer problem in multi-task learning by introducing a task awareness concept, resulting in improved performance over classic MTL solutions and setting new state-of-the-art results on EXIST-2021 and HatEval-2019 benchmarks for detecting sexism, hate speech, and toxic language.
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.