Transparent Semantic Spaces: A Categorical Approach to Explainable Word Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fabregat-Hernández, Ares, Palanca, Javier, Botti, Vicent
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912557805076480
author Fabregat-Hernández, Ares
Palanca, Javier
Botti, Vicent
author_facet Fabregat-Hernández, Ares
Palanca, Javier
Botti, Vicent
contents The paper introduces a novel framework based on category theory to enhance the explainability of artificial intelligence systems, particularly focusing on word embeddings. Key topics include the construction of categories $\mathcal{L}_T$ and $\mathcal{P}_T$, providing schematic representations of the semantics of a text $ T $, and reframing the selection of the element with maximum probability as a categorical notion. Additionally, the monoidal category $\mathcal{P}_T$ is constructed to visualize various methods of extracting semantic information from $T$, offering a dimension-agnostic definition of semantic spaces reliant solely on information within the text. Furthermore, the paper defines the categories of configurations Conf and word embeddings $\mathcal{Emb}$, accompanied by the concept of divergence as a decoration on $\mathcal{Emb}$. It establishes a mathematically precise method for comparing word embeddings, demonstrating the equivalence between the GloVe and Word2Vec algorithms and the metric MDS algorithm, transitioning from neural network algorithms (black box) to a transparent framework. Finally, the paper presents a mathematical approach to computing biases before embedding and offers insights on mitigating biases at the semantic space level, advancing the field of explainable artificial intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20701
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transparent Semantic Spaces: A Categorical Approach to Explainable Word Embeddings
Fabregat-Hernández, Ares
Palanca, Javier
Botti, Vicent
Artificial Intelligence
Computation and Language
Category Theory
The paper introduces a novel framework based on category theory to enhance the explainability of artificial intelligence systems, particularly focusing on word embeddings. Key topics include the construction of categories $\mathcal{L}_T$ and $\mathcal{P}_T$, providing schematic representations of the semantics of a text $ T $, and reframing the selection of the element with maximum probability as a categorical notion. Additionally, the monoidal category $\mathcal{P}_T$ is constructed to visualize various methods of extracting semantic information from $T$, offering a dimension-agnostic definition of semantic spaces reliant solely on information within the text. Furthermore, the paper defines the categories of configurations Conf and word embeddings $\mathcal{Emb}$, accompanied by the concept of divergence as a decoration on $\mathcal{Emb}$. It establishes a mathematically precise method for comparing word embeddings, demonstrating the equivalence between the GloVe and Word2Vec algorithms and the metric MDS algorithm, transitioning from neural network algorithms (black box) to a transparent framework. Finally, the paper presents a mathematical approach to computing biases before embedding and offers insights on mitigating biases at the semantic space level, advancing the field of explainable artificial intelligence.
title Transparent Semantic Spaces: A Categorical Approach to Explainable Word Embeddings
topic Artificial Intelligence
Computation and Language
Category Theory
url https://arxiv.org/abs/2508.20701