Department of IT Engineering, Sookmyung Women's University, Seoul, Republic of Korea.
Department of Computer Engineering, Sunmoon University, Asan, Republic of Korea.
Big Data. 2021 Aug;9(4):279-288. doi: 10.1089/big.2020.0274. Epub 2021 Mar 2.
Recently, emotion recognition in conversation (ERC) has become more crucial in the development of diverse Internet of Things devices, especially closely connected with users. The majority of deep learning-based methods for ERC combine the multilayer, bidirectional, recurrent feature extractor and the attention module to extract sequential features. In addition to this, the latest model utilizes speaker information and the relationship between utterances through the graph network. However, before the input is fed into the bidirectional recurrent module, detailed intrautterance features should be obtained without variation of characteristics. In this article, we propose a residual-based graph convolution network (RGCN) and a new loss function. Our RGCN contains the residual network (ResNet)-based, intrautterance feature extractor and the GCN-based, interutterance feature extractor to fully exploit the intra-inter informative features. In the intrautterance feature extractor based on ResNet, the elaborate context feature for each independent utterance can be produced. Then, the condensed feature can be obtained through an additional GCN-based, interutterance feature extractor with the neighboring associated features for a conversation. The proposed loss function reflects the edge weight to improve effectiveness. Experimental results demonstrate that the proposed method achieves superior performance compared with state-of-the-art methods.
最近，对话中的情感识别（ERC）在各种物联网设备的发展中变得更加重要，特别是与用户密切相关。基于深度学习的 ERC 方法大多将多层、双向、递归特征提取器和注意力模块结合起来，以提取序列特征。除此之外，最新的模型还通过图网络利用说话人信息和话语之间的关系。然而，在将输入输入双向递归模块之前，应该在不改变特征的情况下获得详细的话语内特征。在本文中，我们提出了一种基于残差的图卷积网络（RGCN）和一种新的损失函数。我们的 RGCN 包含基于残差网络（ResNet）的话语内特征提取器和基于图卷积网络（GCN）的话语间特征提取器，以充分利用话语内和话语间的信息特征。在基于 ResNet 的话语内特征提取器中，可以生成每个独立话语的精细上下文特征。然后，通过基于 GCN 的附加话语间特征提取器和对话中的相邻关联特征，可以获得浓缩特征。所提出的损失函数反映了边权重以提高有效性。实验结果表明，与最先进的方法相比，所提出的方法具有更好的性能。
