面向自然语言处理任务的高效最近邻不确定性估计
Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks
AI总结：
本文提出$k$NN-UE方法，结合邻居距离与标签比例进行不确定性估计，在多个NLP任务上优于基线，并验证了近似最近邻搜索可在不明显损失性能的情况下降低推理开销。
摘要：
模型预测的可信度对于现实世界中的安全关键应用至关重要。然而，深度神经网络常常存在不确定性估计方面的问题，例如校准误差。在本研究中，我们提出了$k$-最近邻不确定性估计（$k$NN-UE），这是一种新的不确定性估计方法，不仅利用邻居的距离，还利用邻居中标签的比例。在情感分析、自然语言推理和命名实体识别上的实验表明，我们提出的方法在多个校准和不确定性指标上优于基线方法和最近的基于密度的方法。此外，我们的分析表明，近似最近邻搜索技术在适当结合时，可以降低推理开销，而不会显著降低不确定性估计性能。
英文摘要：
Trustworthiness in model predictions is crucial for safety-critical applications in the real world. However, deep neural networks often suffer from the issues of uncertainty estimation, such as miscalibration. In this study, we propose $k$-Nearest Neighbor Uncertainty Estimation ($k$NN-UE), which is a new uncertainty estimation method that uses not only the distances from the neighbors, but also the ratio of labels in the neighbors. Experiments on sentiment analysis, natural language inference, and named entity recognition show that our proposed method outperforms the baselines and recent density-based methods in several calibration and uncertainty metrics. Moreover, our analyses indicate that approximate nearest neighbor search techniques reduce the inference overhead without significantly degrading the uncertainty estimation performance when they are appropriately combined.
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。
