The Semantic Link Network is a semantics modeling method for effective information services. This paper proposes a new text summarization approach that extracts Semantic Link Network from scientific paper consisting of language units of different granularities as nodes and semantic links between the nodes, and then ranks the nodes to select Top-k sentences to compose summary. A set of assumptions for reinforcing representative nodes is set to reflect the core of paper. Then, Semantic Link Networks with different types of node and links are constructed with different combinations of the assumptions. Finally, an iterative ranking algorithm is designed for calculating the weight vectors of the nodes in a converged iteration process. The iteration approximately approaches a stable weight vector of sentence nodes, which is ranked to select Top-k high-rank nodes for composing summary. We designed six types of ranking models on Semantic Link Networks for evaluation. Both objective assessment and intuitive assessment show that ranking Semantic Link Network of language units can significantly help identify the representative sentences. This work not only provides a new approach to summarizing text based on extraction of semantic links from text but also verifies the effectiveness of adopting the Semantic Link Network in rendering the core of text. The proposed approach can be applied to implementing other summarization applications such as generating an extended abstract, the mind map and the bulletin points for making the slides of a given paper. It can be easily extended by incorporating more semantic links to improve text summarization and other information services.
Bibliographical note© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
This work was supported in part by the National Science Foundation of China under Grant 61075074 and Grant 61640212, in part by the
National Science and Technology Development Plan under Grant 2016YFB1000505, in part by the Research Funding of Guangzhou
University, and in part by the International Research Network on Cyber-Physical-Social Intelligence consisting of Guangzhou University,
Aston University, Key Laboratory of Intelligent Information Processing at the Institute of Computing Technology in Chinese Academy of
Sciences, and the University of Chinese Academy of Sciences (all units are equal).
- Semantics modeling
- natural language processing
- text summarization