Material Detail

This video was recorded at Slovenian KDD Conference on Data Mining and Data Warehouses (SiKDD), Ljubljana 2011. Multi-document summarization is a process of automatic creation of a compressed version of the given collection of documents. Recently, the graph-based models and ranking algorithms have been extensively researched by the extractive document summarization community. While most work to date focuses on sentence-level relations in this paper we present graph model that emphasizes not only sentence level relations but also the influence of under sentence level relations (e.g. a part of sentence similarity). By using the proven cognitive psychology model (the Event-Indexing model) and semantic role parsing for generating the frame graph, we establish the bases for distinguishing the sentence level relations. Based on this model, we developed an iterative frame and sentence ranking algorithm, based on the existing well known PageRank algorithm. Experiments are conducted on the DUC 2004 data sets and the ROUGE (Recall-Oriented Understudy for Gisting Evaluation) evaluation results demonstrate the advantages of the proposed approach.

Disciplines:

• Science and Technology  / Computer Science