Deep Convolutional Neural Network Textual Features and Multiple Kernel Learning for Utterance-level Multimodal Sentiment Analysis
Deep Convolutional Neural Network Textual Features and Multiple Kernel Learning for Utterance-level Multimodal Sentiment Analysis
复制标题
DOI：
10.18653/v1/d15-1303
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Soujanya Poria;E. Cambria;Alexander Gelbukh
中科院分区：
文献类型：
--
作者：
Soujanya Poria;E. Cambria;Alexander Gelbukh
我们提出了一种从短文本中提取特征的新方法，该方法基于深度卷积神经网络内层的激活值。我们使用提取的特征在多模态情感分析的短视频片段代表一句话。我们使用文本，视觉和音频模态的组合特征向量来训练基于多核学习的分类器，该分类器擅长异构数据。我们获得了14%的性能提高，比最先进的，并提出了一个并行化的决策级数据融合方法，这是更快，但精度稍低。
We present a novel way of extracting features from short texts, based on the activation values of an inner layer of a deep convolutional neural network. We use the extracted features in multimodal sentiment analysis of short video clips representing one sentence each. We use the combined feature vectors of textual, visual, and audio modalities to train a classifier based on multiple kernel learning, which is known to be good at heterogeneous data. We obtain 14% performance improvement over the state of the art and present a parallelizable decision-level data fusion method, which is much faster, though slightly less accurate.