Author : Vaishali Fulmali Prof K.P. Moholkar

Question-answer systems are referred to as intelligent systems that can be used to provide answers for the questions which are asked by the user based on certain facts or rules stored in the knowledge base. The typical problem in natural language processing is automatic question-answering. The question-answering is aiming at designing systems that can automatically answer a question, in the same way as a human can find answers to questions. Community question answering (CQA) services were becoming popular over the past few years. It allows the members of the community to post as well as answer the questions. It enables general users to seek information from a comprehensive set of questions that are well-answered. CQA texts are relatively noisy and therefore the implementation of the classic text mining methods such as a bag of a word doesn’t lead to good results. In the proposed system, a deep learningbased model is used for automatic question-answering. First, the questions and answers are embedded. The deep neural network is trained to find the similarity between questions. The best answer for each question is found as the one with the highest similarity score. The purpose of the proposed system is designing an automated question answering system. The proposed system uses a hierarchically clustered dataset. This dataset is the basis for the QA system. Finally, this system can provide a satisfactory answer for the asker.

Keywords: Social network, Community based question answering, recurrent neural networks, LSTM, deep learning