Multilingual language models have gained significant attention in recent
years, enabling the development of applications that cater to diverse
linguistic contexts. In this paper, we present a comprehensive evaluation of
three prominent multilingual language models: mBERT, XLM-R, and GPT-3. Using
the self-supervised task of next token prediction, we assess their performance
across a diverse set of languages, with a focus on understanding the impact of
resource availability, word order, language family, and script type on model
accuracy. Our findings reveal that resource availability plays a crucial role
in model performance, with higher resource levels leading to improved accuracy.
We also identify the complex relationship between resource availability,
language families, and script types, highlighting the need for further
investigation into language-specific characteristics and structural variations.
Additionally, our statistical inference analysis identifies significant
features contributing to model performance, providing insights for model
selection and deployment. Our study contributes to a deeper understanding of
multilingual language models and informs future research and development to
enhance their performance and generalizability across languages and linguistic
contexts.

多语言语言模型的综合评估：mBERT、XLM-R 和 GPT-3 在具有不同语言环境的各种语言上的性能评估，发现资源可用性对模型性能有重要影响，并且资源可用性、语言家族和脚本类型之间存在复杂关系，为模型选择和部署提供了见解。

mBBC: 探索多语迷宫

mBBC: Exploring the Multilingual Maze

Optimal resource allocation is gaining a renewed interest due its relevance
as a core problem in managing, over time, cloud and high-performance computing
facilities. Semi-Bandit Feedback (SBF) is the reference method for efficiently
solving this problem. In this paper we propose (i) an extension of the optimal
resource allocation to a more general class of problems, specifically with
resources availability changing over time, and (ii) Bayesian Optimization as a
more efficient alternative to SBF. Three algorithms for Bayesian Optimization
for Resource Allocation, namely BORA, are presented, working on allocation
decisions represented as numerical vectors or distributions. The second option
required to consider the Wasserstein distance as a more suitable metric to use
into one of the BORA algorithms. Results on (i) the original SBF case study
proposed in the literature, and (ii) a real-life application (i.e., the
optimization of multi-channel marketing) empirically prove that BORA is a more
efficient and effective learning-and-optimization framework than SBF.

本文提出了一种 Bayesian Optimization 算法用于解决最优资源分配问题，相比于传统的 Semi-Bandit Feedback 方法具有更高的效率和学习优化能力。

BORA：贝叶斯优化用于资源分配

BORA: Bayesian Optimization for Resource Allocation

In many self-organising systems the ability to extract necessary resources
from the external environment is essential to the system's growth and survival.
Examples include the extraction of sunlight and nutrients in organic plants, of
monetary income in business organisations and of mobile robots in swarm
intelligence actions. When operating within competitive, ever-changing
environments, such systems must distribute their internal assets wisely so as
to improve and adapt their ability to extract available resources. As the
system size increases, the asset-distribution process often gets organised
around a multi-scale control topology. This topology may be static (fixed) or
dynamic (enabling growth and structural adaptation) depending on the system's
internal constraints and adaptive mechanisms. In this paper, we expand on a
plant-inspired asset-distribution model and introduce a more general
multi-scale model applicable across a wider range of natural and artificial
system domains. We study the impact that the topology of the multi-scale
control process has upon the system's ability to self-adapt asset distribution
when resource availability changes within the environment. Results show how
different topological characteristics and different competition levels between
system branches impact overall system profitability, adaptation delays and
disturbances when environmental changes occur. These findings provide a basis
for system designers to select the most suitable topology and configuration for
their particular application and execution environment.

在此研究中，我们扩展了一种植物灵感的资产分配模型，引入了一个更普遍的多尺度模型，适用于更广泛的自然和人工系统领域，研究了多尺度控制流程拓扑对系统自适应资产分配能力的影响，结果表明不同的拓扑特征和系统分支之间的不同竞争水平对整个系统的盈利能力、适应延迟和环境变化时的干扰产生影响。这些发现为系统设计人员选择最适合其特定应用和执行环境的拓扑和配置提供了基础。