Automatic Text Summarization using Document Clustering Named Entity Recognition

Due to the rapid development of internet technology, social media and popular research article databases have generated many open text information. This large amount textual information leads 'Big Data'. Textual can be recorded repeatedly about an event or topic on different websites. Text summarization (TS) is emerging field that helps produce summary from a single multiple documents. The redundant in documents difficult, hence part all sentences may omitted without changing gist document. TS organized as exposition collect accents its special position, rather than being semantic nature. Non-ASCII characters pronunciation, including tokenizing lemmatization are involved generating summary. work has proposed Entity Aware Summarization using Document Clustering (EASDC) technique extract multi-documents. Named Recognition (NER) vital work. topics key terms identified NER technique. Extracted entities ranked with Zipf’s law sentence clusters formed k-means clustering. Cosine similarity-based used eliminate similar multi-documents unique EASDC evaluated CNN dataset it shown improvement 1.6 percentage when compared baseline methods Textrank Lexrank.