双注意力 hateXplain：在多任务背景下考虑数据的序列特性进行可解释性
Bi-Attention HateXplain : Taking into account the sequential aspect of data during explainability in a multi-task context
AI总结：
BiAtt-BiRNN-HateXplain模型通过双向注意力和BiRNN层，提升多任务环境下仇恨言论检测的可解释性和准确性，减少偏见。
摘要：
互联网和在线社交网络的技术进步为人类带来了许多好处。同时，这种增长也导致了仇恨言论的增加，成为全球的主要威胁。为了提高用于仇恨言论检测的黑盒模型的可靠性，事后方法如LIME、SHAP和LRP在训练分类模型后提供解释。相比之下，基于HateXplain基准的多任务方法同时学习解释和分类。然而，HateXplain基于算法的结果表明，预测的注意力在应为恒定时变化较大。这种注意力变化可能导致解释不一致、预测不稳定和学习困难。为了解决这个问题，我们提出了BiAtt-BiRNN-HateXplain（双向注意力BiRNN HateXplain）模型，该模型比LLMs在透明性需求方面更易于解释，并且通过BiRNN层考虑输入数据的序列特性进行可解释性。因此，如果解释被正确估计，借助多任务学习（可解释性和分类任务），模型可以更好地分类，并减少与社区相关的无意偏见错误。在HateXplain数据上的实验结果表明，检测性能、可解释性和无意偏见的减少都有明显改善。
英文摘要：
Technological advances in the Internet and online social networks have brought many benefits to humanity. At the same time, this growth has led to an increase in hate speech, the main global threat. To improve the reliability of black-box models used for hate speech detection, post-hoc approaches such as LIME, SHAP, and LRP provide the explanation after training the classification model. In contrast, multi-task approaches based on the HateXplain benchmark learn to explain and classify simultaneously. However, results from HateXplain-based algorithms show that predicted attention varies considerably when it should be constant. This attention variability can lead to inconsistent interpretations, instability of predictions, and learning difficulties. To solve this problem, we propose the BiAtt-BiRNN-HateXplain (Bidirectional Attention BiRNN HateXplain) model which is easier to explain compared to LLMs which are more complex in view of the need for transparency, and will take into account the sequential aspect of the input data during explainability thanks to a BiRNN layer. Thus, if the explanation is correctly estimated, thanks to multi-task learning (explainability and classification task), the model could classify better and commit fewer unintentional bias errors related to communities. The experimental results on HateXplain data show a clear improvement in detection performance, explainability and a reduction in unintentional bias.
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。
