Word2Vec on Toki Pona shows distributional patterns suffice for semantic structure even at extreme vocabulary reduction, and incidental non-core tokens tighten rather than disrupt clusters.
Evaluation of Word Vector Representations by Subspace Alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Examining the Limits of Word2Vec with Toki Pona
Word2Vec on Toki Pona shows distributional patterns suffice for semantic structure even at extreme vocabulary reduction, and incidental non-core tokens tighten rather than disrupt clusters.