Word2Vec's effectiveness at generating semantic embeddings has been widely validated, yet it has been tested almost exclusively on languages with large vocabulary inventories. This study examines whether Word2Vec can successfully capture semantic relationships within an extremely reduced vocabulary using data from Toki Pona, a constructed language with approximately 130 words. We sourced 1.4 million sentences (7.95 million tokens) from the Toki Pona community for training. Approximately 23% of sentences in the corpus contain non-Toki Pona tokens such as named entities, loanwords, and neologisms. To investigate whether this linguistic noise enhances or hinders performance -- a topic rarely addressed in word embedding literature -- we trained two distinct models: one retaining these incidental tokens and another filtering them out completely. Evaluation was conducted using quantitative methods measuring word proximity to semantic category centroids, automated silhouette scores via agglomerative clustering, and qualitative analysis utilizing representational similarity matrices compared against English. The results indicate that while sparse, non-core tokens do not affect the relative structure of the learned embeddings, they actually draw similar words closer together in the vector space. Importantly, Word2Vec's effectiveness depends more on distributional patterns than lexicon size even at this extreme lower bound.

翻译：Word2Vec在生成语义嵌入方面的有效性已得到广泛验证，但其测试几乎完全集中在词汇量庞大的语言上。本研究使用道本语（一种仅包含约130个单词的人造语言）的数据，检验Word2Vec能否在极度精简的词汇库中成功捕获语义关系。我们从道本语社区收集了140万条句子（795万个词元）用于训练。语料库中约23%的句子包含非道本语词元，如命名实体、外来词和新造词。为探究这种语言噪音是增强还是阻碍模型性能（这是词嵌入文献中鲜少涉及的研究方向），我们训练了两个独立模型：一个保留这些偶发词元，另一个将其完全过滤。评估采用定量方法（测量单词与语义类别中心的接近度）、基于凝聚层次聚类的自动轮廓系数分析，以及利用表征相似性矩阵与英语进行对比的定性分析。结果表明：尽管稀疏的非核心词元不影响已习得嵌入的相对结构，但它们实际上会使相似单词在向量空间中更加紧密聚集。重要的是，即使在词汇量达到极端下限的情况下，Word2Vec的有效性仍更依赖分布模式而非词表规模。