English to Hindi Cross-Lingual Text Summarizer using TextRank Algorithm

Abstract

Cross-Lingual Summarizer develops a gist of the extract written in English in the National Language of India Hindi. This helps non-anglophonic people to understand what the text says in Hindi. The extractive method of summarization is being used in this paper for summarizing the article. The summary generated in English is then translated into Hindi and made available for Hindi Readers. The Hindi readers get the heart of the article they want to read. Due to the Internet’s explosive growth, access to a vast amount of information is now efficient but getting harder and harder. An approach to text extraction summarization that captures the aboutness of the text document was discussed in this paper. One of the many uses for natural language processing (NLP) that significantly affects our daily lives is text summarization. Who has the time to read through complete articles, documents, or books to determine whether they are helpful with the expansion of digital media and the profusion of articles published? The technique was created using TextRank, which was determined using the idea of PageRank established for each page on a website. The presented approach builds a graph with sentences as nodes and the weight of the edge connecting two sentences as its nodes. Modified inverse sentence-cosine frequency similarity gives different words in a sentence different weights. The success of the procedure is demonstrated by the performance evaluation that supported the summary technique.