Skip to content
Open access

Semantic Representations based on Neural Topic Models

Oct 2026 · Journal of universal computer science (Online) · 0 citations · 26 references

TL;DR

A Neural Topic Model called ABT is presented which leverages semantic vector spaces (derived from language models) to uncover latent semantic representations in text collections to explore the themes covered by a given textual collection and analyze them as a hierarchical structure of topics.

Abstract

Topic Models is a tool to extract semantics from textual collections. However, in spite of extensive work on topic modeling, including its evaluation using Language Models (LM), there is need for more research to measure, analyze and validate the topics learned. To this end, we present a Neural Topic Model called ABT which leverages semantic vector spaces (derived from language models) to uncover latent semantic representations in text collections. ABT enables one to explore the themes covered by a given textual collection and analyze them as a hierarchical structure of topics. We demonstrate the effectiveness of ABT by analyzing two text corpora: (1) CliCR, a collection of 10,539 real clinical cases; and (2) MovieLens, a dataset consisting of 9,742 movie titles. We have experimented with different language models to investigate the effects of using specific tasks to tune the neural network. The topics that resulted from our study highlighted concepts that are shown to be effectively used as prominent topics to represent the datasets. The results show that each experimented LM focuses on distinct features to produce the topics and may generate topics with different grades of generality and specificity. Our study sheds light on recent findings of the related literature, which state that the topic coherence metric does not align with assessments performed by human evaluators.

Read PDF

Similar papers

Open access Oct 2026

A topic-based framework for interpretable and sparse semantic representations

In computational approaches to language, semantic representations produced by modern deep learning systems are often encoded as high-dimensional latent vectors that are difficult to interpret. By contrast, cognitive science has emphasized the need for semantic representations with interpretable and cognitively meaningf...

Ming Song, Qing Cai · 0 citations
#large language models Open access Oct 2026

Classical Tricks for Better Topics: Can Traditional Text Mining Techniques Improve Generative Topic Modeling?

Topic modeling is widely used to discover and organize latent themes in large text collections. While recent embedding-based methods have improved topic discovery by leveraging dense semantic representations, they typically represent topics as lists of keywords, often providing limited insights into the underlying them...

Isis Meira, Isabella Leite, Gabriel Assis et al. · 0 citations
#machine learning Preprint Oct 2026

Sentence-Level Topic Modeling with Lexical and Contextual Evidence

Experiments show that SentenceETM consistently improves sentence-level topic assignment over state-of-the-art approaches, and a case study of a presidential debate shows how sentence-level topics reveal how candidates handle the same subjects.

Federica Granese, S. Villata, C. Bouveyron · 0 citations
Open access Nov 2026

Semantic Topic Discovery for Curriculum Analysis of NCERT Chemistry Textbooks Using Transformer-Based Language Models

Objectives: This study aims to develop and compare an AI-based approach for analyzing the conceptual structure of NCERT Chemistry curricula through BERTopic and Latent Dirichlet Allocation (LDA). Method: The textbooks from Classes XI and XII (19 chapters) were gathered from the official NCERT website repository and con...

Saifullah Rahimi, Hiren Joshi, Hardik Joshi · 0 citations
Book Open access Nov 2026

LSRTopic: Contextual Sparse Topic Modeling via Corpus-Vocabulary Alignment

Topic modeling still struggles to combine contextual expressiveness with lexical interpretability. Sparse models are transparent but semantically limited, whereas dense contextual models capture meaning at the cost of direct interpretability. We argue that Learned Sparse Representations (LSR) offer a promising alternat...

A. Machado, C. França, Antônio Pereira et al. · 0 citations

UvA-DARE (Digital Academic

Christophe Van Gysel, E. Kanoulas · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.