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

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8130–8141 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 8130 Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement Mengting Hu1,2 Honglei Guo3∗ Shiwan Zhao3 Hang Gao4 Zhong Su3 1 College of Software, Nankai University 2 Tianjin Key Laboratory of Operating System 3 IBM Research - China 4 Institute for Public Safety Research, Tsinghua University mthu@nankai.edu.cn, gaohang@mail.tsinghua.edu.cn {guohl,zhaosw,suzhong}@cn.ibm.com Abstract A mind-map is a diagram that represents the central concept and key ideas in a hierarchi- cal 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 sen- tence pair to generate the directed semantic graph for this document. The computation complexity increases exponentially with the length of the document. Moreover, it is diffi- cult to capture the overall semantics. To deal with the above challenges, we propose an effi- cient mind-map generation network that con- verts 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 re- sults demonstrate that the proposed approach is more effective and efficient than the exist- ing methods. The inference time is reduced by thousands of times compared with the existing methods. The case studies verify that the gen- erated mind-maps better reveal the underlying semantic structures of the document. 1 Introduction A mind-map is a hierarchical diagram that can de- pict the central concept, linked with the major ideas and other ideas branch out from these (Kudeli´c et al., 2011; Wei et al., 2019). It is organized in cog- nitive structures and much easier to understand than plain text (Dhindsa et al., 2011). Thus in practice, it can be utilized for education resources, organizing, and planning. Many tools can help people make mind-map manually, such as FreeMind, MindGe- nius and Visual Mind, etc (Kudeli´c et al., 2011). To save human labors, some automatic methods have been proposed to generate mind-map from text, which focus on analyzing the semantic relations ∗Honglei Guo is the corresponding author. 0. Three basic tips on writing a good research paper title. 1. The primary function of a title is to provide a precise summary of the paper’s content, so keep the title brief and clear. 2. Captures the reader’s attention by important points and avoiding lengthy title. 3. Differentiates the paper from the other papers of the same subject area through appropriate descriptive words. 0. basic tips, a good research paper title 1. precise summary, brief and clear 2. Captures the reader’s attention 3. appropriate descriptive words (a) Original text (b) Salient-sentence-based mindmap (SSM) (c) Key-snippet-based mindmap (KSM) 0. Three basic tips on writing a good research paper title. 1. The primary function of a title is to provide a precise summary of the paper’s content, so keep the title brief …

Content truncated to 500 words