SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text

TL;DR

This paper introduces SAP-sLDA, a semi-supervised, human-in-the-loop method for learning interpretable topics in text corpora that better preserve semantic relationships in low-dimensional projections.

Contribution

It presents a novel semi-supervised LDA-based approach that incorporates human feedback to improve the interpretability and semantic coherence of document projections.

Findings

More interpretable projections on synthetic data

Preserves semantic relationships better than baseline methods

Requires fewer labels for effective learning

Abstract

A common way to explore text corpora is through low-dimensional projections of the documents, where one hopes that thematically similar documents will be clustered together in the projected space. However, popular algorithms for dimensionality reduction of text corpora, like Latent Dirichlet Allocation (LDA), often produce projections that do not capture human notions of document similarity. We propose a semi-supervised human-in-the-loop LDA-based method for learning topics that preserve semantically meaningful relationships between documents in low-dimensional projections. On synthetic corpora, our method yields more interpretable projections than baseline methods with only a fraction of labels provided. On a real corpus, we obtain qualitatively similar results.