Chatbot is a technology that is used to mimic human behavior using natural. There are different types of Chatbot that can be used as agent in various business domains in order to increase the service and satisfaction. For any business domain, it requires a base to be built for that domain and design an information retrieval system that can respond the user with a piece of documentation or sentences. The core component of a Chatbot is Natural Language (NLU) which has been impressively improved by deep learning. But we often lack such properly built NLU modules and requires more to build it from scratch for high quality conversations. This may fresh learners to build a Chatbot from scratch with simple and using small dataset, although it may have reduced, rather than building high quality data driven methods. This focuses on Named Entity Recognition (NER) and Intent Classification which can be integrated into NLU service of a Chatbot. Named entities be inserted manually in the knowledge base and automatically detected in a sentence. The NER model in the proposed architecture is based on neural network which is trained on manually created entities and using CoNLL-2003 dataset.
No takes yet. Share an insight, caveat, or question.
Nazakat Ali (2020) studied this question.