Extractive Text-Image Summarisation in Hindi

Abstract

: Today’s world has skyrocketed by the gathering and dissemination of huge amounts of data. A lot of this data is in text form which makes it very difficult to store and process. Hindi is the national language of India. Dataset of text-image summarization is not readily available for Hindi language and hence we created a dataset of 40558 news articles with images for the task and created extractive summaries for them. We did the evaluation using ROGUE and BELU metrics.