Review on natural language processing tasks for text documents

摘要

This paper mainly focused on Natural Language Processing (NLP) tasks such as Coreference resolution, Discourse Analysis, Named Entity Recognition (NER), Sentiment Analysis, Word sense disambiguation (WSD), Part of Speech (POS), etc. It also reviewed each NLP task with various application areas, with their different approaches and their corresponding methods. This survey is done to decide which NLP task will be better for preprocessing of search keyword, which in turn uses for appropriate matching to desired text documents. Finally it comes to a conclusion that POS tagging and chunking, both will be a better option for preprocessing of keyword, so that its resultant keyword will give desired and important text document.