Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement

TL;DR

This paper introduces an efficient method for automatic mind-map generation from documents using sequence-to-graph conversion and reinforcement learning-based graph refinement, significantly reducing computation time and improving semantic structure capture.

Contribution

It proposes a novel sequence-to-graph model with a reinforcement learning-based refinement module, enhancing efficiency and semantic accuracy over existing methods.

Findings

Inference time reduced by thousands of times

Generated mind-maps better reveal semantic structures

Method outperforms existing approaches in effectiveness and efficiency

Abstract

A mind-map is a diagram that represents the central concept and key ideas in a hierarchical way. Converting plain text into a mind-map will reveal its key semantic structure and be easier to understand. Given a document, the existing automatic mind-map generation method extracts the relationships of every sentence pair to generate the directed semantic graph for this document. The computation complexity increases exponentially with the length of the document. Moreover, it is difficult to capture the overall semantics. To deal with the above challenges, we propose an efficient mind-map generation network that converts a document into a graph via sequence-to-graph. To guarantee a meaningful mind-map, we design a graph refinement module to adjust the relation graph in a reinforcement learning manner. Extensive experimental results demonstrate that the proposed approach is more effective and efficient than the existing methods. The inference time is reduced by thousands of times compared with the existing methods. The case studies verify that the generated mind-maps better reveal the underlying semantic structures of the document.