OMFM: A Framework of Object Merging Based on Fuzzy Multisets

Information fusion is a process of merging information from multiple sources into a new set of information. Existing work on information fusion is applicable in various scenarios such as multiagent system, group decision making, and multidocument summarization. This paper intends to develop an effective framework to solve object merging problem based on fuzzy multisets. The objects defined in this paper are data segments in document fusion task, referring to the concepts with semantic-related terms of different semantic relations embedded. The fundamental operation is the merge function mapping data segments in multiple fuzzy multisets onto one object, which is a solution. Under this framework, we define quality measures of purity and entropy to quantify the quality of the solutions, balancing accurateness, and completeness of the results. Merge function that yields this kind of solutions is VI-optimal merge function and a series of theoretical properties concerning it are studied. Finally, we investigate the proposed framework in a special application scenario (i.e., document fusion) which is related to the task of multidocument summarization and show how the framework works with illustrative example.

Multidocument Summarization of Engineering Papers Based on Macro- and Microstructure

This paper focuses on automatic summarization of multiple engineering papers. A summarization approach based on documents’ macro- and microstructure has been proposed. The macrostructure consists of a list of ranked topics from engineering papers. Topics are discovered by extracting and grouping frequently appearing word sequences into equivalence classes. Hence, the macrostructure symbolically presents the topical links in different papers. Meanwhile, the microstructure is defined as the rhetorical structure within a single paper. The identification of microstructure is approached as a classification problem. Each sentence in a paper is automatically labeled with one of the predefined rhetorical categories. Unlike existing summarization methods that first separate documents into nonoverlapping clusters and then summarize each cluster individually, our approach aims to summarize multiple documents according to the characteristics suggested at macro- and microstructure levels. The experimental study showed that our proposed approach outperformed peer systems in terms of recall-oriented understudy for gisting evaluation scores and readers’ responsiveness. In an independent manual categorization task using the summaries generated by our approach and peer systems, we also performed better in terms of precision and recall.