HCDIR：面向在线评论的端到端仇恨语境检测与强度降低模型
HCDIR: End-to-end Hate Context Detection, and Intensity Reduction model for online comments
AI总结：
本文提出端到端模型HCDIR，用于检测社交媒体仇恨评论并降低其强度，通过微调预训练模型检测仇恨词，利用积分梯度识别语境仇恨词，并采用掩码语言建模生成替代词，实验验证了其有效性。
摘要：
警告：本文包含一些可能令部分人群感到冒犯的语言示例。在社交媒体上，检测并减少仇恨性、辱骂性、攻击性评论是一项关键且具有挑战性的任务。此外，很少有研究旨在缓解仇恨言论的强度。虽然研究表明上下文级语义对于检测仇恨评论至关重要，但由于数据集充足，大多数此类研究集中在英语上。相比之下，低资源语言（如印度语言）因数据集有限而研究不足。与仇恨言论检测不同，仇恨强度降低在高资源语言和低资源语言中仍未得到探索。在本文中，我们提出了一种新颖的端到端模型HCDIR，用于社交媒体帖子中的仇恨语境检测和仇恨强度降低。首先，我们微调了多个预训练语言模型以检测仇恨评论，以确定性能最佳的仇恨评论检测模型。然后，我们识别了上下文仇恨词。此类仇恨词的识别通过最先进的可解释学习模型（即积分梯度（IG））得到验证。最后，采用掩码语言建模（MLM）模型来捕捉领域特定细微差别以降低仇恨强度。我们掩蔽了被识别为仇恨的评论中50%的仇恨词，并为这些掩蔽词预测替代词以生成令人信服的句子。从可行句子中优先选择原始仇恨评论的最优替换。我们使用基于自动指标评估（BERTScore）和全面的人工评估，在多个近期数据集上进行了广泛实验。为了增强人工评估的可靠性，我们安排了一组由三位具有不同专业知识的标注者组成的小组。
英文摘要：
Warning: This paper contains examples of the language that some people may find offensive. Detecting and reducing hateful, abusive, offensive comments is a critical and challenging task on social media. Moreover, few studies aim to mitigate the intensity of hate speech. While studies have shown that context-level semantics are crucial for detecting hateful comments, most of this research focuses on English due to the ample datasets available. In contrast, low-resource languages, like Indian languages, remain under-researched because of limited datasets. Contrary to hate speech detection, hate intensity reduction remains unexplored in high-resource and low-resource languages. In this paper, we propose a novel end-to-end model, HCDIR, for Hate Context Detection, and Hate Intensity Reduction in social media posts. First, we fine-tuned several pre-trained language models to detect hateful comments to ascertain the best-performing hateful comments detection model. Then, we identified the contextual hateful words. Identification of such hateful words is justified through the state-of-the-art explainable learning model, i.e., Integrated Gradient (IG). Lastly, the Masked Language Modeling (MLM) model has been employed to capture domain-specific nuances to reduce hate intensity. We masked the 50\% hateful words of the comments identified as hateful and predicted the alternative words for these masked terms to generate convincing sentences. An optimal replacement for the original hate comments from the feasible sentences is preferred. Extensive experiments have been conducted on several recent datasets using automatic metric-based evaluation (BERTScore) and thorough human evaluation. To enhance the faithfulness in human evaluation, we arranged a group of three human annotators with varied expertise.
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。
