论文标题
使用MLB融合的并行意图和插槽预测
Parallel Intent and Slot Prediction using MLB Fusion
论文作者
论文摘要
意图和插槽标识是口语理解（SLU）中的两个重要任务。对于自然语言，这两个任务之间存在很高的相关性。使用复发性神经网络（RNN），卷积神经网络（CNN）和基于注意力的模型，对每种都进行了许多工作。过去的大多数工作都使用了两个单独的模型来进行意图和插槽预测。其中一些还使用了序列到序列类型模型，在评估话语级别的意图后，预测插槽。在这项工作中，我们提出了一种平行的意图和插槽预测技术，其中每个任务都使用单独的双向封盖复发单元（GRU）。我们认为MLB（多模式低级双线性注意网络）融合的用法可改善意图和插槽学习的性能。据我们所知，这是在基于文本问题上使用这种技术的首次尝试。此外，我们提出的方法的表现优于两个基准数据集上意图和插槽预测的现有最新结果
Intent and Slot Identification are two important tasks in Spoken Language Understanding (SLU). For a natural language utterance, there is a high correlation between these two tasks. A lot of work has been done on each of these using Recurrent-Neural-Networks (RNN), Convolution Neural Networks (CNN) and Attention based models. Most of the past work used two separate models for intent and slot prediction. Some of them also used sequence-to-sequence type models where slots are predicted after evaluating the utterance-level intent. In this work, we propose a parallel Intent and Slot Prediction technique where separate Bidirectional Gated Recurrent Units (GRU) are used for each task. We posit the usage of MLB (Multimodal Low-rank Bilinear Attention Network) fusion for improvement in performance of intent and slot learning. To the best of our knowledge, this is the first attempt of using such a technique on text based problems. Also, our proposed methods outperform the existing state-of-the-art results for both intent and slot prediction on two benchmark datasets
