Abstract
Generating meaningful summary for the given natural language text is one of the challenging and popular task in present era. Researchers have come up with various techniques for the abstractive and extractive summarization. This experimental study is focused on the extractive summarization. In graph-based extractive text summarization techniques, the sentences of the input document are used as the nodes of the graph and various similarity measurements are used to weight the edges of the graph. Each node’s rating is determined using the graph ranking algorithms, and the top-ranked nodes (sentences) are then added to the output extractive summary. In this work, we first translate the publicly available dataset into Hindi text using the Google Translate service. Next, we apply a pre-trained multi-lingual transformer to generate embedding vectors of each sentence of the document. We use these embedding vectors as the nodes of the graph. Rest of the approach remains unchanged. At last, we evaluate the generated extractive summaries on the basis on ROUGE score. Evaluation results indicate that the use of pre-trained multi-lingual transformer can be effective to generate more meaningful extractive summaries.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
