arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.03377cs.CLcs.LG
收藏

基于任务感知缓解负迁移的性别歧视、仇恨言论和有毒语言检测

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

Universitat Politècnica de València(瓦伦西亚理工大学);RMIT University(皇家墨尔本理工大学)

Angel Felipe Magnossão de Paula, Paolo Rosso, Damiano Spina

AI总结:

本文提出基于任务感知的多任务学习方法以缓解负迁移问题,并在EXIST-2021和HatEval-2019基准上取得性别歧视、仇恨言论和有毒语言检测的最新最优性能。

摘要:

本文提出了一种缓解负迁移问题的新方法。在机器学习领域,常见策略是采用单任务学习方法,训练一个有监督模型来解决特定任务。训练一个稳健的模型需要大量数据和可观的计算资源,这使得在数据不可用或获取成本高昂的情况下该方案不可行。因此,另一种基于任务间信息共享的解决方案被开发出来:多任务学习(MTL)。尽管多任务学习近期有所发展,负迁移问题仍然有待解决。负迁移是一种当噪声信息在任务之间共享时出现的现象,会导致性能下降。本文基于任务感知概念提出了一种缓解负迁移问题的新方法。所提方法在减少负迁移的同时,相比经典多任务学习方案还带来了性能提升。此外,所提方法已在两个统一架构中实现,用于检测文本评论中的性别歧视、仇恨言论和有毒语言。所提架构在EXIST-2021和HatEval-2019基准上均设立了新的最先进水平。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑