International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 08 Issue: 02 | Feb 2021 www.irjet.net p-ISSN: 2395-0072 © 2021, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 930 Survey on Question Retrieval in Community Question Answering via NON-Negative Matrix Factorization Yogita Puri M.S.Bidve Engineering College,Latur Pankaj Kokane M.S.Bidve Engineering College,Latur ABSTRACT: CQA is useful in answering real-world questions. CQA provide a solution to human. Question retrieval in CQA can automatically find the foremost relevant and up to date questions that are solved by other users. We propose an alternative thanks to addressing the word ambiguity and word mismatch problems by taking advantage of probably rich semantic information drawn from other languages. The translated words from other languages via non-negative matrix factorization. Contextual information is exploited during the interpretation from one language to a different language by using Google Translate. Thus, word ambiguity is often solved supported the contextual information when questions are translated. Multiple words that have similar meanings in one language are also translated into a singular word or some words in a very foreign language. it's a word-based translation language model for retrieval with a question likelihood model for an answer. We use a translated representation by alternative enriching the first question with the words from other languages in CQA. We translate English questions into other four languages using Google translate which takes into account contextual information during translation. If we translate the question word by word, it discards the contextual information. We’d expect that such a translation would not be able to solve the word ambiguity problem. Keywords Community Question Answering, Statically Machine Translation, Non Matrix Factorization, Google Translator, Recursive Neural Network. 1. INTRODUCTION To make community question answering portals more useful, it is necessary for the system to be able to fetch the questions asked in other languages moreover. this may give the user a wide range of pre answered inquiries to rummage around for solutions to his/her problem. Current systems fail to try to so. Also, these systems fetch related questions supported the keywords in it. Thus, if there's an issue which is said to the subject but having other keywords, then that question isn't retrieved, this is a serious drawback of a system as there is many circumstances where a semantically related question but not having similar keywords isn't retrieved. The proposed the system shows the way to retrieve questions which are associated with the asked question but asked in other languages moreover because the questions that are associated with the subject but not having similar keywords. The proposed system shows that this will be achieved when these questions are retrieved semantically instead of using keywords. It is found that, in most cases, an automatic approach cannot obtain results that are nearly as good as those generated by human intelligence. together with the proliferation and improvement of underlying communication technologies, community Question Answering (CQA) has emerged as an extremely popular alternative to accumulate information online, owning to the subsequent facts. a. Information seekers are able to post their specific questions on any topic and acquire answers provided by other participants. By leveraging community efforts, they're able to bounce back answers than simply using search engines. as compared with automated CQA systems, CQA usually receives answers with better quality as they're generated supported human intelligence. c. Over times, an amazing number of QA pairs are accumulated in their repositories, and it facilitates the preservation and search of answered questions. Related Work Learning the Multilingual Translation Representations for Question Retrieval in Community Question Answering via Non- negative Matrix Factorization In this paper they propose to employ statistical machine translation to improve question retrieval and enrich the question representation with the translated words from other languages via matrix factorization. They also Proposes a way of fetching previously asked questions which are asked in different different languages but are related to the asked question after the development of web 2.0, www became very interactive and lot of new kinds of applications emerged based on web 2.0. ----------------------------------------------------------------------------------------------------------------------------------