Natural Language Information Extraction Through Non-Factoid Question and Answering System (NLIEQA Non-Factoid)

Over the years, the retrieval of information from unstructured data has increased significantly. The availability of unstructured data, or to be precise, data in the form of natural language is available in abundance. The main role of a Question and Answering System is to process the natural language query and generate a concise answer to it. There are many works done in recent times, which have given a Question and Answering System that helps in answering factoid or list-type queries asked in natural language, but most of them have made use of structured data. The proposed Natural Language Information Extraction through Question and Answering for Non-Factoid cases (NLIEQA Non-Factoid) accepts data and the query fired by the user in the form of natural language text, processes them, and produces the desirable answer. It avoids training the system and the use of Structured Query Language (SQL) for storage and processing. Another advantage of the model is that it can handle complex queries. The model has a strong use of Named Entity Recognition (NER) for classification and extraction of the answers. It also makes use of Stanford’s Natural Language Tool Kit (NLTK) for tokenizing, tagging, and chunking of the text.