Augmenting Customer Support with an NLP-based Receptionist

Abstract

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.

arXiv comment11 pages, 2 figures, Symposium in Information and Human Language Technology (STIL)

References in corpus (5)

• Recent Advances and Challenges in Task-oriented Dialog System
• COTA: Improving the Speed and Accuracy of Customer Support through Ranking and Deep Networks
• A Survey on Dialog Management: Recent Advances and Challenges
• Attention Fusion Networks: Combining Behavior and E-mail Content to Improve Customer Support
• Analyzing HPC Support Tickets: Experience and Recommendations