Intent Detection and Slot Filling with Capsule Net Architectures for a Romanian Home Assistant

Abstract

As virtual home assistants are becoming more popular, there is an emerging need for supporting languages other than English. While more wide-spread or popular languages such as Spanish, French or Hindi are already integrated into existing home assistants like Google Home or Alexa, integration of other less-known languages such as Romanian is still missing. This paper explores the problem of Natural Language Understanding (NLU) applied to a Romanian home assistant. We propose a customized capsule neural network architecture that performs intent detection and slot filling in a joint manner and we evaluate how well it handles utterances containing various levels of complexity. The capsule network model shows a significant improvement in intent detection when compared to models built using the well-known Rasa NLU tool. Through error analysis, we observe clear error patterns that occur systematically. Variability in language when expressing one intent proves to be the biggest challenge encountered by the model.

Inquiring Natural Language Processing Capabilities on Robotic Systems through Virtual Assistants: A Systemic Approach

“…In the 7th article [19] , the Capsule Net architectures are used, for Intent detection and slot filling for a Romanian home assistant. The Capsule Net architecture is a type of deep learning neural network that aims to overcome the limitations of the traditional Convolutional Neural Network (CNN), by capturing the hierarchical relationships between features.…”

Control of a Drone in Virtual Reality Using MEMS Sensor Technology and Machine Learning

“…• a level corresponding to the input data; • a level corresponding to the output data; • one or more hidden levels that represent the computational engine of the MLP [38] network.…”

Natural Language Processing for Smart Healthcare

“…The difficulties of natural language understanding come from the diversity, ambiguity, and potential dependence of natural language, making slow progress in natural language understanding compared with other NLP techniques. After years of development in both general areas and smart healthcare, the mainstream route of NLU is still to use various methods to conduct slot filling and intent detection [106]- [108]. NLU is the core of multiple intelligent agents, assuming a role in understanding human intentions during human-machine interactions [106], [109], [110], medical queries [107], [108], etc.…”

“…After years of development in both general areas and smart healthcare, the mainstream route of NLU is still to use various methods to conduct slot filling and intent detection [106]- [108]. NLU is the core of multiple intelligent agents, assuming a role in understanding human intentions during human-machine interactions [106], [109], [110], medical queries [107], [108], etc.…”