A Novel Approach for Semantic Similarity Measurement for High Quality Answer Selection in Question Answering using Deep Learning Methods
Darshana V. Vekariya, Nivid Limbasiya · 2020
Question retrieval and high-quality answer retrieval is the main task in Question-answering system. It is a real-world application of NLP technologies. The major challenge of QA is the exact selection of high-quality responses w.r.t. given questions and by doing that it will also minimize the time of finding a similar question and high-quality answer. The colossal measure of information accessible, however getting the correct data open when required is significant. So, for a new question, it gives a list of similar and related questions, which could satisfy response, information needs to the user, without waiting for new questions to be answered by users. QA engines attempt to let you ask the question the way you normally ask. QA can have two domains Open Domain Question Answering and Closed Domain Question Answering. In Open-area there's no any unique area, customers are free to ask any question, the device will deliver the solution from the internet and deliver a respective solution to the person. In a closed domain, QA users are restricted to some particular domain. We have used four datasets name as STSB(Semantic textual similarity benchmark), MRPC(Microsoft research paraphrase corpus), SICK(Sentences involving compositional knowledge) and Wikipedia dataset. And we've got as compared our proposed machine with different contemporary strategies and our proposed technique offers the excellent result many of the other techniques.