trustmebro.to/r/…
✓ checked
trust me, bro:
here is the receipt.
the claim

Semantic similarity between words is measured using distributional and vector space models

the verdict
SUPPORTED
the evidence backs this
Recorded sources
7 sources for · 0 against

Counts group repeated records of the same source within each side. They do not measure evidence strength or source independence.

Is it true that semantic similarity between words is measured using distributional and vector space models?

Yes. Multiple studies demonstrate that distributional models and vector spaces are standard methods for measuring semantic similarity between words and texts.

Verdict: SUPPORTED · 7 sources for, 0 against · Last checked

The analysis

The claim states that semantic similarity between words is measured using distributional and vector space models. All retrieved papers that directly investigate this topic rely on word embeddings, vector spaces, or distributional semantics to quantify semantic similarity, providing full support for the claim with no conflicting evidence.

Evidence for · 7
A Vector Space for Distributional Semantics for Entailment
2016
The paper uses distributional semantic vector spaces to capture semantic similarity and lexical relations.
Get citation
Henderson, J. & Popa, D. N. (2016). A Vector Space for Distributional Semantics for Entailment. doi.org. https://doi.org/10.18653/v1/P16-1193

See more details
More for · 6
LessLex: Linking Multilingual Embeddings to SenSe Representations of LEXical Items
2020
The research utilizes embeddings in a semantic space to test and evaluate conceptual and lexical similarity.
Get citation
Colla, D., Mensa, E., & Radicioni, D. (2020). LessLex: Linking Multilingual Embeddings to SenSe Representations of LEXical Items. doi.org. https://doi.org/10.1162/coli_a_00375

Refining Word Representations by Manifold Learning
2019
The study refines pre-trained word representations in vector spaces to improve measures of semantic similarity.
Get citation
Chu, Y., Lin, H., Yang, L., Diao, Y., Zhang, S., & Fan, X. (2019). Refining Word Representations by Manifold Learning. doi.org. https://doi.org/10.24963/ijcai.2019/749

Lexical semantics enhanced neural word embeddings
2022
The work aims to improve vector space models in deriving semantic similarity from neural word embeddings.
Get citation
Yang, D., Li, N., Zou, L., & Ma, H. (2022). Lexical semantics enhanced neural word embeddings. doi.org. https://doi.org/10.1016/j.knosys.2022.109298

Centroid analysis: Inferring concept representations from open-ended word responses.
2026
The study maps responses onto a semantic vector space to measure concept representations and semantic similarity.
Get citation
A, P. & F, G. (2026). Centroid analysis: Inferring concept representations from open-ended word responses.. doi.org. https://doi.org/10.3758/s13428-026-03031-y

Leveraging large language models and embedding representations for enhanced word similarity computation.
2025
The framework transforms semantic representations into vector embeddings to measure word similarity accurately.
Get citation
X, P., H, J., J, C., M, L., & X, C. (2025). Leveraging large language models and embedding representations for enhanced word similarity computation.. doi.org. https://doi.org/10.1038/s41598-025-31102-1

Learning semantic similarity from sentence pairs using hybrid features centric approach and explainable siamese neural networks.
2026
The research employs semantic embeddings and vector models to compute sentence-level semantic similarity.
Get citation
W, Z. & C, H. (2026). Learning semantic similarity from sentence pairs using hybrid features centric approach and explainable siamese neural networks.. doi.org. https://doi.org/10.1371/journal.pone.0345540

What does the evidence say?

The claim states that semantic similarity between words is measured using distributional and vector space models. All retrieved papers that directly investigate this topic rely on word embeddings, vector spaces, or distributional semantics to quantify semantic similarity, providing full support for the claim with no conflicting evidence.

Receipt History
first checked05 Aug 2026
judged → SUPPORTED · 8405 Aug 2026
Anyone with this link can read the claim and its public receipt, including any personal information in that text. Open permanent receipt.
Check your own claim
Challenge the receipt
Requests are recorded for review. This does not start an automatic check or guarantee a response time.

See the evidence timeline

Citation formatting by citeproc-js (Frank Bennett) and the Citation Style Language project. Source and licenses.

This receipt is an automated verdict against our published method · not an opinion about any author or publication.
Terms · Privacy · How verdicts work