Variations of the Similarity Function of TextRank for Automated Summarization
This research addresses the need for better summarization tools in natural language processing, but it is incremental as it builds upon the existing TextRank method.
The authors tackled the problem of improving automated text summarization by proposing new similarity functions for the TextRank algorithm, with some variants achieving significant improvements in performance metrics on the same dataset as the original work.
This article presents new alternatives to the similarity function for the TextRank algorithm for automatic summarization of texts. We describe the generalities of the algorithm and the different functions we propose. Some of these variants achieve a significative improvement using the same metrics and dataset as the original publication.