发表机构
Faculty of Mathematics and Computer Science Babeş-Bolyai University（巴比什-波雅依大学数学与计算机科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对语言识别，将字符和二元语法频率分布建模为成分向量，经CLR变换映射到特定子空间，结合CLR变换特征与拉普拉斯平滑提出管道方法，在六种语言上评估，该方法在不同文本长度下准确率高，提供了高效且可解释的语言识别替代方案。
AI 中文摘要
语言识别通常使用神经架构或统计n元语法模型。神经方法通常需要大量计算资源，而基于频率的经典方法提供了高效的线性时间性能，但依赖于并非总是适用于成分数据的距离度量。这项工作将字符和二元语法频率分布建模为受限于单纯形的成分向量，并通过中心对数比率（CLR）变换双射地映射到\(\mathbb{R}^D\)的\((D - 1)\)维零和子空间，其中欧几里得距离对应于艾奇逊距离。提出了一个管道，将CLR变换的一元语法和二元语法特征与拉普拉斯平滑相结合以解决稀疏性。该方法在六种语言上进行了评估。实验结果表明，该方法在不同文本长度上实现了稳健的准确率，对较长序列表现出强大性能。这些发现表明，成分表示为语言识别提供了一种确定性且计算高效的替代方案，特别是在可解释性和低资源消耗至关重要的情况下。
英文摘要
Language identification is commonly addressed using either neural architectures or statistical n-gram models. Neural approaches typically require substantial computational resources, whereas classical frequency-based methods offer efficient linear-time performance, but rely on distance metrics that are not always appropriate for compositional data. This work models character and bigram frequency distributions as compositional vectors constrained to the simplex and mapped via the centered log-ratio (CLR) transformation bijectively onto the $(D-1)$-dimensional zero-sum subspace of $\mathbb{R}^D$, where Euclidean distances correspond to Aitchison distances. A pipeline is proposed, combining CLR-transformed unigram and bigram features with Laplace smoothing to address sparsity. The method is evaluated on six languages. Experimental results show that the proposed approach achieves robust accuracy across different text lengths, with strong performance for longer sequences. These findings indicate that compositional representations provide a deterministic and computationally efficient alternative for language identification, particularly in settings where interpretability and low resource consumption are essential.
