Multi-Document Summarization using Fuzzy Logic and Firefly Algorithm

Abstract

Due to the huge amount of documents in the internet made it difficult to get useful information. Automatic text summarization is a good solution for such problem, which is based on a selection of important sentences from one or multi-document without losing the main ideas of the original text. In this paper a new method was proposed which depend upon selection of seven features for every sentence in the documents. These features fed into the fuzzy logic system to give scores to these sentences. Firefly algorithm applied as association rule mining to minimize the set of rules generated by the fuzzy logic system and finally redundancy reduce performed to remove redundant sentences. The proposed model is performed using dataset supplied by the Text Analysis Conference (TAC-2011) for English documents. The results were measured by using Recall-Oriented Understudy for Gisting Evaluation (ROUGE). The obtained results support the effectiveness of the proposed model.