Question Answering System for Applicant Support by Using Modern Messengers

Abstract

There is an increasing interest to the instant messaging applications, messengers. These applications allow us to interact with other users and include a functionality that can help us to implement bots that automate various business processes or provide information services. In this paper, we consider a specialized question answering system that uses today’s messaging services infrastructure to support university applicants. We gathered a corpus of applicants questions throughout two years and developed an information retrieval model that helps us to find similar questions in the corpus. Applicants can type their questions using a natural language without any formal requirements to phrase construction or using special templates. If the system is unable to find a relevant answer, the user can directly address the question to representatives of the university. The system was implemented with the use of modern cloud services that are provided by Amazon. We used serverless computations and NoSQL data bases, so we had to develop an architecture of the system in that way. Since the system contains sensitive personal data and provide personalized service, we must focus our attention on security. We proposed the means that must improve the safety of the system, more specifically, authentification process that can be used without the explicit use of personal data, however, this is a future work. At present we test our system and evaluate its quality of information retrieval.