In this paper, we consider the extent to which the transformer-based Dense
Passage Retrieval (DPR) algorithm, developed by (Karpukhin et. al. 2020), can
be optimized without further pre-training. Our method involves two particular
insights: we apply the DPR context encoder at various phrase lengths (e.g.
one-sentence versus five-sentence segments), and we take a
confidence-calibrated ensemble prediction over all of these different
segmentations. This somewhat exhaustive approach achieves start-of-the-art
results on benchmark datasets such as Google NQ and SQuAD. We also apply our
method to domain-specific datasets, and the results suggest how different
granularities are optimal for different domains

本文考虑如何优化基于 Transformer 的密集通道检索算法，具体方法包括在不同短语长度下使用 DPR 上下文编码器和采取置信度校准的集成预测。研究表明，该方法在 Google NQ 和 SQuAD 等标准数据集以及特定领域的数据集上，均取得了最先进的结果。

置信度校准的集合稠密短语检索

Confidence-Calibrated Ensemble Dense Phrase Retrieval

Robust machine learning models with accurately calibrated uncertainties are
crucial for safety-critical applications. Probabilistic machine learning and
especially the Bayesian formalism provide a systematic framework to incorporate
robustness through the distributional estimates and reason about uncertainty.
Recent works have shown that approximate inference approaches that take the
weight space uncertainty of neural networks to generate ensemble prediction are
the state-of-the-art. However, architecture choices have mostly been ad hoc,
which essentially ignores the epistemic uncertainty from the architecture
space. To this end, we propose a Unified probabilistic architecture and weight
ensembling Neural Architecture Search (UraeNAS) that leverages advances in
probabilistic neural architecture search and approximate Bayesian inference to
generate ensembles form the joint distribution of neural network architectures
and weights. The proposed approach showed a significant improvement both with
in-distribution (0.86% in accuracy, 42% in ECE) CIFAR-10 and
out-of-distribution (2.43% in accuracy, 30% in ECE) CIFAR-10-C compared to the
baseline deterministic approach.

本研究提出了一种统一的概率架构与权重集成神经架构搜索方法，利用概率神经架构搜索和近似贝叶斯推理的进展，从神经网络架构和权重的联合分布生成集成模型，取得了较大的进步。

统一的概率神经架构和权重组合提高模型鲁棒性

Unified Probabilistic Neural Architecture and Weight Ensembling Improves Model Robustness

This paper has been written to mark 25 years of operational medium-range
ensemble forecasting. The origins of the ECMWF Ensemble Prediction System are
outlined, including the development of the precursor real-time Met Office
monthly ensemble forecast system. In particular, the reasons for the
development of singular vectors and stochastic physics - particular features of
the ECMWF Ensemble Prediction System - are discussed. The author speculates
about the development and use of ensemble prediction in the next 25 years.

本文介绍了欧洲中期天气预报中心 (ECMWF) 的多模式集合预报系统的发展历程，特别是它独特的奇异向量和随机物理特征，并对未来 25 年的集合预测发展和应用进行了推测。