1. [a] Develop a program in any language [ C,C++,core Java,pure python without NLTK] for identifying all the Entity names occurring in any article. The entity types could be PER[Person],GPE[Geo Political Entity], ORG[Organization], LOC[ location]. You should provide one input article from ‘The Hindu’ website [https://www.thehindu.com] and the outputs of all these entity names and their types should be written to a entity1.txt file. Explain the functioning of the program and also attach the code. [ 5 marks] [b] Develop a program in python with NLTK for the same purpose. Provide the same input and write to an output Entity2.txt file. Explain how much NLTK has simplified your effort in a paragraph. [2 marks]
2. Develop a Extractive summarization program in python only that takes the same news article as the input and produce a summary. The input article should be maximum one page [250 words] and the summary should be limited to 50-75 words. You should provide the program as well the logic. [3 marks]