Effective Elytron Vespid-B rank BiLSTM classifier for Multi-Document Summarization.

Multi-Document Summarization is the progression of extracting the pertinent information from a group of documents and weeding out the irrelevant information to create a concise text representation of the documents. This summarization initiates comprehensive information and a coherent flow of the summary, which reduces the effort and time of the individuals. In this research, the document summarization is performed using the Elytron Vespid-B rank-based Bidirectional Long Short-Term Memory (BiLSTM) classifier, which reduces the multi documents into a summarized document. The main contribution of the research depends on the proposed Elytron Vespid Beetle (Elytron Vespid-B) optimization algorithm that effectively enhanced the interactive and individual behavior of the Elytron-B that reduced the computational complexity of the classifier by optimally tuning the hyperparameters. The proposed Elytron vespid-B rank BiLSTM classifier achieved the values of 0.61, 0.35, and 0.61, for the metrics f1 measure for the varied rouges 1, 2, and l, which are believed to be more efficient than the existing approaches, and used to reveal the effectiveness of the research. [ABSTRACT FROM AUTHOR]