论文标题
DialogConv：一个轻巧的全卷积网络，用于多视图响应选择
DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection
论文作者
论文摘要
当前基于端到端的基于基于端到端的对话系统主要基于具有注意机制的复发神经网络或变形金刚。尽管已经取得了令人鼓舞的结果，但这些模型通常会遭受缓慢的推理或大量参数的影响。在本文中，我们提出了一种新颖的轻巧完全卷积架构，称为DialogConv，以进行响应选择。 DialogConv专门建立在卷积之上，以提取上下文和响应的匹配功能。对话是在3D视图中建模的，其中DialogogConv在嵌入视图，单词视图和话语视图上执行卷积操作，以从多个上下文视图中捕获更丰富的语义信息。在四个基准数据集中，与最先进的基线相比，DialogogConv的尺寸平均约为8.5倍，CPU和GPU设备的速度分别较快为79.39倍和10.64倍。同时，DialogConv实现了响应选择的竞争有效性。
Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or huge number of parameters. In this paper, we propose a novel lightweight fully convolutional architecture, called DialogConv, for response selection. DialogConv is exclusively built on top of convolution to extract matching features of context and response. Dialogues are modeled in 3D views, where DialogConv performs convolution operations on embedding view, word view and utterance view to capture richer semantic information from multiple contextual views. On the four benchmark datasets, compared with state-of-the-art baselines, DialogConv is on average about 8.5x smaller in size, and 79.39x and 10.64x faster on CPU and GPU devices, respectively. At the same time, DialogConv achieves the competitive effectiveness of response selection.
