In this paper, we show how a Portuguese BERT model can be combined with structured data in order to deploy a chatbot based on a finite state machine to create a conversational AI system that helps a real-estate company to predict its client's contact motivation. The model achieves human level results in a dataset that contains 235 unbalanced labels. Then, we also show its benefits considering the business impact comparing it against classical NLP methods.
@article{arxiv.2112.01959,
title = {Augmenting Customer Support with an NLP-based Receptionist},
author = {André Barbosa and Alan Godoy},
journal= {arXiv preprint arXiv:2112.01959},
year = {2021}
}
Comments
11 pages, 2 figures, Symposium in Information and Human Language Technology (STIL)