Genetic algorithms are optimizing algorithms, inspired by natural evolution. Investigations on genetic algorithms reveal that these algorithms are different from other search-based optimizing methods. In most optimizing techniques based on a point, the analysis is done according to only some of the decision-making regulations. These techniques could yield an incorrect answer in the searching spaces having several maximum points. In other words, it is possible that the local maximum point be obtained as the answer. Hence, genetic algorithms could also be used in mathematical programming. The common techniques utilized in this field are not effective since they need a series of limitations such as functions continuity and differentiation to be optimized. Moreover, there is no originality in these techniques and this is why the genetic algorithm method could be used in these cases, especially for non-linear programing to reach desirable outcomes.
The goal of this paper is to compare summaries generated by different automatic text summarization methods and those generated by human beings. To achieve this end, we did two series of experiments: in the first one, we employed automatically produced extractive summaries; in the second one, manually-produced summaries obtained by several English teachers were used. Our automatic summaries were obtained using Fuzzy method and Vector approach. Using Rouge evaluation system, we compared the manually-produced summaries and the automatically-produced ones. Rouge evaluation of generated summaries indicated the superiority of summaries produced by humans over the automatically produced summaries. On the other hand, the comparison between the generated summaries showed that summaries produced by Fuzzy method were much more acceptable and understandable compared to summaries produced by Vector approach. This can provide support for the replacement of manually generated summaries by summaries produced using Fuzzy method in certain cases where real time summaries are needed.
This work proposes an approach to address the problem of improving content selection in automatic text summarization by using some statistical tools. This approach is a trainable summarizer, which takes into account several features, for each sentence to generate summaries. First, we investigate the effect of each sentence feature on the summarization task. Then we use all features in combination to train cellular automata (CA), genetic programming approach and fuzzy approach in order to construct a text summarizer for each model. Furthermore, we use trained models to test summarization performance. The proposed approach performance is measured at several compression rates on a data corpus composed of 17 English scientific articles. This article shows that some features are more important to construct models rather than other.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.