A Hybrid Model for Text Summarization Using Natural Language Processing

Text summarization plays an important role in the area of natural language processing. The need for information all over world to solve specific problems keeps on increasing daily. This poses a greater challenge as data stored internet has gradually increased exponentially time. Finding out relevant and manually summarizing it short time is challenging tedious task human being. Summarization aims compress source text into more concise form while preserving its overall meaning. Two major categories methods exist namely: extractive abstractive. technique concentrates determining key themes using frequency analysis sentences corpus text. Abstractive write new summary with newly generated texts which do not appear itself. paper presents hybrid model both abstractive techniques. Term Frequency (TF) – Inverse Document (IDF) was used T5 Transformers summarization. Iterative Incremental Methodology adopted study. emerged best choice compared had been hypothesized study when accuracy execution considered.