论文标题
弱监督标签平滑
Weakly Supervised Label Smoothing
论文作者
论文摘要
在神经学习（L2R）模型的背景下，我们研究了一种广泛使用的正则化技术标签平滑（LS）。 LS结合了地面标签与均匀分布，鼓励模型对其预测的信心降低。我们分析了非相关的文档在特定方面的采样方式和LS的有效性之间的关系，讨论了如何在相关和非相关文档类之间捕获LS捕获“隐藏的相似性知识”。我们通过测试课程学习方法，即从LS开始和仅使用地面真实标签的迭代术后进一步分析LS是有益的。受到神经L2R模型的调查的启发，我们提出了一种称为弱监督标签平滑（WSL）的新技术，该技术利用了负面采样文档的检索得分，作为在修改基础真实标签的过程中作为弱监督信号。 WSL易于实现，不需要修改神经排名架构。我们在三个检索任务检索中进行的实验，类似的问题检索和对话响应排名表，这些响应排名显示了基于BERT的排名者WSL可以带来一致的有效性提高。源代码可在https://anonymon.4open.science/r/DAC85D48-6F71-4261-A7D8-040DA6021C52/上获得。
We study Label Smoothing (LS), a widely used regularization technique, in the context of neural learning to rank (L2R) models. LS combines the ground-truth labels with a uniform distribution, encouraging the model to be less confident in its predictions. We analyze the relationship between the non-relevant documents-specifically how they are sampled-and the effectiveness of LS, discussing how LS can be capturing "hidden similarity knowledge" between the relevantand non-relevant document classes. We further analyze LS by testing if a curriculum-learning approach, i.e., starting with LS and after anumber of iterations using only ground-truth labels, is beneficial. Inspired by our investigation of LS in the context of neural L2R models, we propose a novel technique called Weakly Supervised Label Smoothing (WSLS) that takes advantage of the retrieval scores of the negative sampled documents as a weak supervision signal in the process of modifying the ground-truth labels. WSLS is simple to implement, requiring no modification to the neural ranker architecture. Our experiments across three retrieval tasks-passage retrieval, similar question retrieval and conversation response ranking-show that WSLS for pointwise BERT-based rankers leads to consistent effectiveness gains. The source code is available at https://anonymous.4open.science/r/dac85d48-6f71-4261-a7d8-040da6021c52/.
