A Robust Slot Filling Model based on LSTM and CRF for IoT Voice Interaction
Mourad Jbene, Smail Tigani, Rachid Saadane, Abdellah Chehri · 2022 IEEE Globecom Workshops (GC Wkshps) · 2022
The Internet Of Things (IoT) is an emerging paradigm representing a network of infrastructure connecting different types of devices in different places. Recently, IoT-based Conversational systems gained more attention, providing users with a new human-computer interaction mode. These new systems allow users to interact with the IoT ecosystem through a virtual assistant. They also heavily rely on Natural Language Processing (NLP) techniques for intelligent and efficient communication. Understanding the user’s needs is the first step toward a more humanized IoT interaction system. This can be achieved using Natural language understanding (NLU) modules. Slot Filling is one of the core sub-tasks in NLU. It is an active research area focusing on extracting attribute values from the user’s utterance. In this study, we propose an LSTM-based model for slot filling. The model benefits from contextual embeddings extracted from the BERT transformer model, the attention mechanism, and the conditional random field (CRF) that is known to model strong dependence among adjacent tags in the output sequence. Experiments show that our model achieved competitive results on two widely used benchmark datasets.