Summarization tool for multimedia data

Abstract

Text summarization is an important Natural Language Processing problem. Manual text summarization is a laborious and time-consuming task. Owing to the advancements in the field of Natural Language Processing, this task can be effectively moved from manual to automated text summarization. This paper proposes a model named Term Frequency-Inverse Document Frequency (TF-IDF) Summarization Tool which implements a text analytics approach called TF-IDF to generate a meaningful summary. TF-IDF is used to identify the topic or context of the text statistically. As data today is mostly unstructured in nature, this paper aims to explore a combination of NLP techniques such as Speech Recognition and Optical Character Recognition to summarize multimedia data as well. The TF-IDF Summarization Tool is seen to produce summaries with Jaccard's Similarity value of 67% and Rogue-1 of 64.9%, Rogue-2 of 48.2%, and Rogue-L of 56.4% based on a self-developed dataset.