One of the most popular research topics in recent years has been the development of a Natural Language Processing system capable of extracting answers to natural language queries from a given context. Question Answering is a computer science discipline that focuses on building systems that automatically answer questions posed by humans in natural language. It is related to information retrieval and natural language processing. It aims to provide precise answers in natural language in response to the user's questions. We used various NLP datasets in this project to train an NLP model for developing a context aware question answering system. In order to help with the task, we trained multiple models using BERT and LSTM architecture and performed a variety of processing tasks. To fit our model, we converted data to textual data, token sized, stemmed, and embedded it. The final model was then deployed to a front end application, which takes context data and questions and, after processing and utilizing the deployed model, provides answers based on its learning.
Key words: Machine learning, prediction, expert system, context-aware, natural language processing (NLP).
|
