Self-attention networks (SAN) have shown promising performance in various Natural Language Processing (NLP) scenarios, especially in machine translation. One of the main points of SANs is the strength of capturing long-range and multi-scale dependencies from the data. In this paper, we present a novel intent detection system which is based on a self-attention network and a Bi-LSTM. Our approach shows improvement by using a transformer model and deep averaging network-based universal sentence encoder compared to previous solutions. We evaluate the system on Snips, Smart Speaker, Smart Lights, and ATIS datasets by different evaluation metrics. The performance of the proposed model is compared with LSTM with the same datasets.
@article{arxiv.2006.15585,
title = {Self-Attention Networks for Intent Detection},
author = {Sevinj Yolchuyeva and Géza Németh and Bálint Gyires-Tóth},
journal= {arXiv preprint arXiv:2006.15585},
year = {2020}
}
Comments
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)