Chatbot: A Conversational Agent employed with Named Entity Recognition Model using Artificial Neural Network

Chatbot is a technology that is used to mimic human behavior using natural\nlanguage. There are different types of Chatbot that can be used as\nconversational agent in various business domains in order to increase the\ncustomer service and satisfaction. For any business domain, it requires a\nknowledge base to be built for that domain and design an information retrieval\nbased system that can respond the user with a piece of documentation or\ngenerated sentences. The core component of a Chatbot is Natural Language\nUnderstanding (NLU) which has been impressively improved by deep learning\nmethods. But we often lack such properly built NLU modules and requires more\ntime to build it from scratch for high quality conversations. This may\nencourage fresh learners to build a Chatbot from scratch with simple\narchitecture and using small dataset, although it may have reduced\nfunctionality, rather than building high quality data driven methods. This\nresearch focuses on Named Entity Recognition (NER) and Intent Classification\nmodels which can be integrated into NLU service of a Chatbot. Named entities\nwill be inserted manually in the knowledge base and automatically detected in a\ngiven sentence. The NER model in the proposed architecture is based on\nartificial neural network which is trained on manually created entities and\nevaluated using CoNLL-2003 dataset.\n