Next Article in Journal
Prediction by Empirical Similarity via Categorical Regressors
Previous Article in Journal
Real-Time Vehicle Make and Model Recognition System
Open AccessArticle

Enhancing Domain-Specific Supervised Natural Language Intent Classification with a Top-Down Selective Ensemble Model

1
Abaka Holdings Ltd. 1, London SW1E 5HX, UK
2
The Alan Turing Institute, London NW1 2DB, UK
3
Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages, University of Cambridge, Cambridge CB3 9DB, UK
*
Author to whom correspondence should be addressed.
Mach. Learn. Knowl. Extr. 2019, 1(2), 630-640; https://doi.org/10.3390/make1020037
Received: 1 March 2019 / Revised: 12 April 2019 / Accepted: 16 April 2019 / Published: 18 April 2019
Natural Language Understanding (NLU) systems are essential components in many industry conversational artificial intelligence applications. There are strong incentives to develop a good NLU capability in such systems, both to improve the user experience and in the case of regulated industries for compliance reasons. We report on a series of experiments comparing the effects of optimizing word embeddings versus implementing a multi-classifier ensemble approach and conclude that in our case, only the latter approach leads to significant improvements. The study provides a high-level primer for developing NLU systems in regulated domains, as well as providing a specific baseline accuracy for evaluating NLU systems for financial guidance. View Full-Text
Keywords: natural language understanding; dialogue systems; multi-classifier; word embeddings; domain adaptation; conversational artificial intelligence; financial domain; long short-term memory natural language understanding; dialogue systems; multi-classifier; word embeddings; domain adaptation; conversational artificial intelligence; financial domain; long short-term memory
Show Figures

Figure 1

MDPI and ACS Style

Jenset, G.B.; McGillivray, B. Enhancing Domain-Specific Supervised Natural Language Intent Classification with a Top-Down Selective Ensemble Model. Mach. Learn. Knowl. Extr. 2019, 1, 630-640.

Show more citation formats Show less citations formats

Article Access Map by Country/Region

1
Back to TopTop