Self-Attention Networks for Intent Detection

Sevinj Yolchuyeva, Géza Németh, Bálint Gyires-Tóth


Abstract
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.
Anthology ID:
R19-1157
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
1373–1379
Language:
URL:
https://aclanthology.org/R19-1157
DOI:
10.26615/978-954-452-056-4_157
Bibkey:
Cite (ACL):
Sevinj Yolchuyeva, Géza Németh, and Bálint Gyires-Tóth. 2019. Self-Attention Networks for Intent Detection. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1373–1379, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Self-Attention Networks for Intent Detection (Yolchuyeva et al., RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-1157.pdf
Data
ATIS