Transparent Semantic Spaces: A Categorical Approach to Explainable Word Embeddings

• URL: http://arxiv.org/abs/2508.20701v1
• Date: Thu, 28 Aug 2025 12:19:34 GMT
• Title: Transparent Semantic Spaces: A Categorical Approach to Explainable Word Embeddings
• Abstract summary: The paper introduces a novel framework based on category theory to enhance the explainability of artificial intelligence systems.<n>Key topics include the construction of categories $ L_T $ and $ P_T $, providing schematic representations of the semantics of a text.
• Score: 0.7200655637873443
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 $ \L_{T} $ and $ \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 $ \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 $ \Emb $, accompanied by the concept of divergence as a decoration on $ \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.

Related papers

• Does Syntax Matter? A Graph-Augmented Variational Topic Model for Computational Social Sciences [51.56484100374058]
  This paper introduces the Structural Contextual Probabilistic Topic Model ( SCPTM), an architecture that incorporates syntactic dependency relations into topic inference.<n>We evaluate seven topic modeling techniques across four corpora differing in register and discourse structure.<n>Results show that SCPTM's neural architecture yields substantial gains in document-topic alignment over generative baselines.
  arXiv  Detail & Related papers  (2026-09-07T17:39:06Z)
• $\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval [99.8640829555514]
  This paper studies the minimal dimension required to embed subset memberships ($m$ elements and $mchoose k$ subsets of at most $k$ elements) into vector spaces, denoted as Minimal Embeddable Dimension (MED)<n>The tight bounds of MED are derived theoretically and supported empirically for various notions of "distances" or "similarities," including the $ell$ metric, inner product and cosine similarity.
  arXiv  Detail & Related papers  (2026-01-28T18:45:43Z)
• Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space [56.37266873329401]
  Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density.<n>We propose $textbfDynamic Large Concept Models (DLCM)$, a hierarchical language modeling framework that learns semantic boundaries from latent representations and shifts from tokens to a compressed concept space where reasoning is more efficient.
  arXiv  Detail & Related papers  (2025-12-31T04:19:33Z)
• Disentangling Latent Embeddings with Sparse Linear Concept Subspaces (SLiCS) [2.7255100506777894]
  Vision-language co-embedding networks, such as CLIP, provide a latent embedding space with semantic information.<n>We propose a supervised dictionary learning approach to estimate a linear synthesis model consisting of sparse, non-negative combinations of groups of vectors.<n>We show that the disentangled embeddings provided by our sparse linear concept subspaces (SLiCS) enable concept-filtered image retrieval.
  arXiv  Detail & Related papers  (2025-08-27T23:39:42Z)
• Alpay Algebra V: Multi-Layered Semantic Games and Transfinite Fixed-Point Simulation [0.0]
  This paper extends the self-referential framework of Alpay Algebra into a multi-layered semantic game architecture.<n>We introduce a nested game-theoretic structure where the alignment process between AI systems and documents becomes a meta-game.<n>We prove a Game Theorem establishing existence and uniqueness of semantic equilibria under realistic cognitive simulation assumptions.
  arXiv  Detail & Related papers  (2025-07-10T15:48:23Z)
• Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations [34.88156871518115]
  Next-token prediction (NTP) optimization leads language models to extract and organize semantic structure from text.<n>We demonstrate that concepts corresponding to larger singular values are learned earlier during training, yielding a natural semantic hierarchy.<n>This insight motivates orthant-based clustering, a method that combines concept signs to identify interpretable semantic categories.
  arXiv  Detail & Related papers  (2025-05-13T08:46:04Z)
• Towards Generalized and Training-Free Text-Guided Semantic Manipulation [123.80467566483038]
  Text-guided semantic manipulation refers to semantically editing an image generated from a source prompt to match a target prompt.<n>We propose a novel $textitGTF$ for text-guided semantic manipulation, which has the following attractive capabilities.<n>Our experiments demonstrate the efficacy of our approach, highlighting its potential to advance the state-of-the-art in semantics manipulation.
  arXiv  Detail & Related papers  (2025-04-24T05:54:56Z)
• Lattice-preserving $\mathcal{ALC}$ ontology embeddings with saturation [50.05281461410368]
  An order-preserving embedding method is proposed to generate embeddings of OWL representations. We show that our method outperforms state-the-art theory-of-the-art embedding methods in several knowledge base completion tasks.
  arXiv  Detail & Related papers  (2023-05-11T22:27:51Z)
• Interpreting Embedding Spaces by Conceptualization [2.620130580437745]
  We present a novel method of understanding embeddings by transforming a latent embedding space into a comprehensible conceptual space. We devise a new evaluation method, using either human rater or LLM-based raters, to show that the vectors indeed represent the semantics of the original latent ones.
  arXiv  Detail & Related papers  (2022-08-22T15:32:17Z)
• Reasoning in the Description Logic ALC under Category Semantics [0.0]
  We present a reformulation of the usual set-theoretical semantics of the description logic $mathcalALC$ with general TBoxes by using categorical language. In this setting, $mathcalALC$ concepts are represented as objects, concept subsumptions as arrows, and memberships as logical quantifiers over objects and arrows of categories.
  arXiv  Detail & Related papers  (2022-05-10T14:03:44Z)
• Unsupervised Semantic Segmentation by Distilling Feature Correspondences [94.73675308961944]
  Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. We present STEGO, a novel framework that distills unsupervised features into high-quality discrete semantic labels. STEGO yields a significant improvement over the prior state of the art, on both the CocoStuff and Cityscapes challenges.
  arXiv  Detail & Related papers  (2022-03-16T06:08:47Z)
• TopicNet: Semantic Graph-Guided Topic Discovery [51.71374479354178]
  Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner. We introduce TopicNet as a deep hierarchical topic model that can inject prior structural knowledge as an inductive bias to influence learning.
  arXiv  Detail & Related papers  (2021-10-27T09:07:14Z)
• Top2Vec: Distributed Representations of Topics [0.0]
  Topic modeling is used for discovering latent semantic structure, usually referred to as topics, in a large collection of documents. We present $texttttop2vec$, which leverages joint document and word semantic embedding to find topics. Our experiments demonstrate that $texttttop2vec$ finds topics which are significantly more informative and representative of the corpus trained on than probabilistic generative models.
  arXiv  Detail & Related papers  (2020-08-19T20:58:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.