Make Any Collection Navigable: Methods for Constructing and Evaluating Hypergraph of Text

2026-04-28

AI Summary

This study addresses the challenge of automatically constructing hypergraph structures from arbitrary text collections to support flexible navigation and effectively evaluating their navigational quality. To this end, the authors propose a general Hypergraph of Text (HoT) construction framework that integrates traditional methods such as TF-IDF with large language models (LLMs) to generate hyperedges. They introduce, for the first time, a novel metric termed “effort ratio” to quantitatively assess the structural quality and navigational efficiency of text hypergraphs. Experimental results demonstrate that lightweight TF-IDF-based approaches achieve effort ratios comparable to those of LLM-based methods, confirming their effectiveness in semantic browsing tasks and offering a scalable, efficient pathway for designing text navigation systems.

Abstract

One reason the Web is more useful than a simple collection of documents is that the structure created by hyperlinks enables flexible navigation from one web page to another. However, hyperlinks are typically created manually and cannot fully capture a corpus' implicit semantic structures. Is there a general way to make an arbitrary collection navigable? Recent work has formalized this problem generally as constructing a Hypergraph of Text (HoT), which provides a formal mathematical structure for supporting navigation and browsing. However, how to construct and evaluate a Hypergraph of Text remains a challenge. In this paper, we propose and study several methods for constructing a HoT. We also propose a novel quantitative metric, effort ratio, for evaluating the structural quality of a constructed HoT. Experimental results show that even simple TF-IDF baselines can match LLM-based methods on our proposed effort ratio metric.

Problem

• Hypergraph of Text
• navigability
• text collection
• semantic structure
• navigation

Innovation

• Hypergraph of Text
• effort ratio
• navigable collections
• text navigation
• structural evaluation