Examining the Limits of Word2Vec with Toki Pona

arXiv cs.CL Papers

Summary

This paper investigates whether Word2Vec can generate meaningful semantic embeddings for Toki Pona, a constructed language with only ~130 words, using a corpus of 1.4 million sentences, and examines the effect of non-Toki Pona tokens on embedding quality.

arXiv:2606.17299v1 Announce Type: new Abstract: 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.
Original Article
View Cached Full Text

Cached at: 06/17/26, 05:39 AM

# Examining the Limits of Word2Vec with Toki Pona
Source: [https://arxiv.org/abs/2606.17299](https://arxiv.org/abs/2606.17299)
[View PDF](https://arxiv.org/pdf/2606.17299)

> Abstract: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\.

## Submission history

From: Daniel Huang \[[view email](https://arxiv.org/show-email/e39c3326/2606.17299)\] **\[v1\]**Mon, 15 Jun 2026 21:07:31 UTC \(985 KB\)

Similar Articles

QuechuaTok: Morphological Boundary Accuracy as a Necessary Metric for Tokenizer Evaluation in Agglutinative Low-Resource Languages

arXiv cs.CL

This paper presents QuechuaTok, a benchmark for evaluating tokenization strategies for Southern Quechua, and introduces Morphological Boundary Accuracy (MorphAcc) as a necessary metric. It shows that BPE achieves low fertility but poor morphological accuracy, while a morphology-aware PRPE tokenizer achieves 83% MorphAcc, demonstrating that fertility rate alone is insufficient for agglutinative languages.