Text Normalization and Summarization Using Advanced Natural Language Processing

Large quantities of data have been generated through various applications such as social media, online platforms, etc., and analyzing these data requires a significant amount of time and effort. Additionally, when encountering complex vocabulary, it would take even longer to comprehend the word and its context within a sentence. Normalization and summarization of this data is the need of the hour. Natural Language Processing (NLP) is used to process data and provide meaningful insight. The summarization technique can effectively condense lengthy texts into simpler and more concise language, as well as identify the main context and themes present in the data. Two ways for summarization are available: one is abstractive and the other one is extractive. Each model has its own set of benefits and drawbacks and can be employed depending on the task's requirements. The proposed model uses its own words and sentences to frame the context of data. This proposed text summarization system is implemented using extractive models, and through a thorough comparison of these two models, the highest efficiency output has been achieved. A strong text-summarization tool is presented through this research article which can collect the main points of big paragraphs. Through results, it has been found that Abstractive Summarization techniques have low scores when compared to Extractive Summarization techniques. For extractive summarization, the 'Text Ranking' method provided better results.