Formal concept analysis for evaluating intrinsic dimension of a natural language

Sergei O. Kuznetsov, Vasilii A. Gromov, Nikita S. Borodin, Andrei M. Divavin
11/17/2023
cs.CLcs.AImath.AT

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Some results of a computational experiment for determining the intrinsic dimension of linguistic varieties for the Bengali and Russian languages are presented. At the same time, both sets of words and sets of bigrams in these languages were considered separately. The method used to solve this problem was based on formal concept analysis algorithms. It was found that the intrinsic dimensions of these languages are significantly less than the dimensions used in popular neural network models in natural language processing.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Language and Its Dimensions: Intrinsic Dimensions of Language Fractal Structures

80% match2023

Language Embeddings Sometimes Contain Typological Generalizations

79% match1 repo52023

Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception

78% match2023

Conceptual structure coheres in human cognition but not in large language models

78% match2023

A Geometric Notion of Causal Probing

77% match1 repo12023

Brain Score Tracks Shared Properties of Languages: Evidence from Many Natural Languages and Structured Sequences

77% match2026

Cite this paper

@article{kuznetsov2023formal,
  title  = {Formal concept analysis for evaluating intrinsic dimension of a natural language},
  author = {Sergei O. Kuznetsov and Vasilii A. Gromov and Nikita S. Borodin and Andrei M. Divavin},
  year   = {2023},
  eprint = {2311.10862},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.10862v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.10862.svg)](https://codeofpaper.com/paper/2311.10862)

Discussion