Abstractive text summarization of multimedia news content using RNN

Abstract

Programmed content outline is a principle NLP procedure that plans to combine a source content into a shorter change. The fast expansion in all sort of information appear over the web requires abstractive summarization from non-concurrent accumulations of substance, picture, sound and video. Here propose an abstractive summarization procedure that joins the strategies of NLP, discourse handling, PC vision and Recurrent Neural Network (RNN) to examine the rich data contained from all type of data and to get better insight of the news content. The key plan is to associate the linguistics openings between multimodal substances. Sound and video frames are major properties in video clips. For sound data, we structure a way to manage explicitly manipulate its interpretation and to find the astounding nature of the translation with sound. For video data, we get acquainted with the both depictions of content and pictures with Computer Vision Technique. Previous researches done on Text Summarization mainly focuses on Extractive method of summarization. In this work, we put forward an Abstractive method of summarization with sequence to sequence architecture. Finally, all the multimodal points are considered to make a literary once-over by increasing the striking nature, non-reiteration, clarity and consideration through the arranged streamlining of sub isolated limits.