PLOS One · 20 Nov 2026
Word embeddings from text corpora: A simulation study on the representation of underlying structures
Willem M. Otteh-index 41, Archibald L.H.M. van Wieringen, Bart J. Koet
Citations by database
Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.
- OpenCitations0
- Crossref0
- Europe PMC0
Citations per year
The current year is still counting.
- 2026 so far0
Abstract
The grounding problem concerns how symbolic representations acquire meaning through connections to what they refer to. For word embeddings learned from text, a related empirical question is how much of the structure that generated the text they retain. This is difficult to test in natural corpora because that structure is generally unknown. We employed a microsimulation methodology to generate a controlled text corpus from a known spatial structure. A virtual language supermarket with 40 shelves organised into four departments (fruit, vegetables, beverages, extras) served as the generative environment. Product sequences from 80,000 simulated shoppers formed a corpus of 804,422 product selections, with each sequence unique. The GloVe algorithm was applied to this corpus to learn 50-dimensional word embeddings, which we compared with the network of shelves. Cosine distance between products correlated with their shortest-path distance in the network (Spearman ρ = 0.79 over all 7,140 product pairs, Mantel p = 0.001), and on average 61% of a product’s network neighbours were among its nearest neighbours in the embedding, against 7% expected by chance. Over ten independent simulations these values were 0.80 ± 0.01 and 0.62 ± 0.02, and shuffling words across the corpus removed the association. Raw co-occurrence counts, PPMI, SVD and word2vec also captured global distance structure but retrieved fewer neighbours (29–50%). Recovery was best with a context window of one word (ρ = 0.93) and was weaker for rare products. K-medoid clustering of all 120 products separated the fruit and extras departments completely, while vegetables and beverages, which are interleaved in the network, were mixed (adjusted Rand index 0.82). UMAP projections followed the network closely (ρ = 0.92) but distorted some parts of it. These findings show that distributional word embeddings can recover much of the structure that a generating process puts into co-occurrence statistics. They do not show that the embeddings are grounded in, or understand, what the words refer to. This controlled simulation provides a reproducible way to measure structural recovery by word embeddings.
What the data shows
- No database records a citation yet, as is usual for a paper this new.
- Willem M. Otte has the highest h-index among the authors (41).
Graph
This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.
Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.
Start with
Cited by 0 papers
Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.
References (62)
What it cites, from open citation data, with Crossref's record of each.
Sign in to see 42 more references
A free account opens the rest of the citing papers and references on every paper’s page.