Language-independent extractive automatic text summarization based on automatic keyword extraction

This study proposes a language and domain independent approach for automatic extractive text summarization (EATS) tasks, which is based on a clustering scheme supported by a genetic algorithm (GA), to find an optimal grouping of sentences. Furthermore, our approach includes a topic modeling algorithm to find the key sentences in clusters based on automatically generated keywords. Our experimental results show that our system outperforms previous methods through the application of two general steps: clustering, which helps to increase coverage, and the addition of semantic information to the model, which facilitates the detection of the key sentences in the clusters and improves precision.