论文标题
自我发项网络的意图检测
Self-Attention Networks for Intent Detection
论文作者
论文摘要
自我发挥的网络（SAN）在各种自然语言处理（NLP）方案中表现出了有希望的表现，尤其是在机器翻译中。 SAN的要点之一是从数据中捕获长距离和多尺度依赖性的强度。在本文中，我们提出了一种基于自我发项网络和BI-LSTM的新型意图检测系统。与以前的解决方案相比，我们的方法通过使用变压器模型和深度平均基于网络的通用句子编码来显示出改进。我们通过不同的评估指标评估了剪切，智能扬声器，智能灯和ATIS数据集的系统。将建议模型的性能与LSTM与相同的数据集进行了比较。
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.
