Self-Attention Networks for Intent Detection
This is an incremental improvement for intent detection in conversational AI systems.
The paper tackles intent detection in NLP by proposing a system combining self-attention networks and Bi-LSTM, showing improvements over LSTM baselines on datasets like Snips and ATIS.
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.