Home // CENTRIC 2018, The Eleventh International Conference on Advances in Human-oriented and Personalized Mechanisms, Technologies, and Services // View article

Natural Language Processing in IBM WatsonAssistant, an Automatic Verification Process

Authors:
Beatriz Consciência
Simão Santos
Pedro Martins
Steven Abrantes
Luis Pombo
Cristina Wanzeller

Keywords: IBM Watson; cognitive computing; neural networks; natural language processing

Abstract:
The exponential growth of Artificial Intelligence powered systems affect us all. IBM Watson Assistant is a great example of one of that AI-powered systems. This paper proposes a strategy that can automate the verification process of generalization capability in the creation of chat-bots using IBM’s platform. K-Fold cross-validation is a popular technique in machine learning for estimating the performance of a learned hypothesis on a data set. Therefore, the proposed method is not new for testing. However, this method is newly applied to a chat-bot application using IBM’s platform. In this paper, the main goal is to make the chat-bot testing process automated so the process can be faster, more productive, and efficient. Algorithms like k-fold cross-validation demonstrate the need for a representative and reasonable amount of data when it comes to training Watson in his ability to learn.

Pages: 14 to 17

Copyright: Copyright (c) IARIA, 2018

Publication date: October 14, 2018

Published in: conference

ISSN: 2308-3492

ISBN: 978-1-61208-670-5

Location: Nice, France

Dates: from October 14, 2018 to October 18, 2018