论文标题
现实世界中不希望的内容检测的整体方法
A Holistic Approach to Undesired Content Detection in the Real World
论文作者
论文摘要
我们提出了一种整体方法，用于构建一个可实现的自然语言分类系统，以适应现实世界中的内容。这样一个系统的成功依赖于精心设计和执行的步骤链，包括内容分类法和标签指令的设计，数据质量控制，主动学习管道以捕获罕见事件，以及多种使模型稳健并避免过度拟合的方法。我们的审核系统经过培训，可以检测一系列不希望的内容，包括性内容，仇恨内容，暴力，自我伤害和骚扰。这种方法概括为各种不同的内容分类法，可用于创建优于现成模型的高质量内容分类器。
We present a holistic approach to building a robust and useful natural language classification system for real-world content moderation. The success of such a system relies on a chain of carefully designed and executed steps, including the design of content taxonomies and labeling instructions, data quality control, an active learning pipeline to capture rare events, and a variety of methods to make the model robust and to avoid overfitting. Our moderation system is trained to detect a broad set of categories of undesired content, including sexual content, hateful content, violence, self-harm, and harassment. This approach generalizes to a wide range of different content taxonomies and can be used to create high-quality content classifiers that outperform off-the-shelf models.
