Text-as-Signal: Quantitative Semantic Scoring with Embeddings, Logprobs, and Noise Reduction

TL;DR

This paper introduces a flexible pipeline that converts text corpora into quantitative semantic signals using embeddings, logprob scoring, and noise reduction, demonstrated on Portuguese AI news articles.

Contribution

It presents a novel, adaptable framework combining embeddings, logprob evaluation, and noise reduction for semantic analysis of large text datasets.

Findings

Supports document-level semantic positioning and corpus characterization.

Integrates Qwen embeddings, UMAP, and anomaly detection into a workflow.

Applicable to AI engineering tasks like corpus inspection and monitoring.

Abstract

This paper presents a practical pipeline for turning text corpora into quantitative semantic signals. Each news item is represented as a full-document embedding, scored through logprob-based evaluation over a configurable positional dictionary, and projected onto a noise-reduced low-dimensional manifold for structural interpretation. In the present case study, the dictionary is instantiated as six semantic dimensions and applied to a corpus of 11,922 Portuguese news articles about Artificial Intelligence. The resulting identity space supports both document-level semantic positioning and corpus-level characterization through aggregated profiles. We show how Qwen embeddings, UMAP, semantic indicators derived directly from the model output space, and a three-stage anomaly-detection procedure combine into an operational text-as-signal workflow for AI engineering tasks such as corpus inspection, monitoring, and downstream analytical support. Because the identity layer is configurable, the same framework can be adapted to the requirements of different analytical streams rather than fixed to a universal schema.