Select-Additive Learning: Improving Cross-individual Generalization in Multimodal Sentiment Analysis
Select-Additive Learning: Improving Cross-individual Generalization in Multimodal Sentiment Analysis
复制标题
DOI：
--
复制
发表时间：
2016-09
期刊：
影响因子：
--
通讯作者：
Haohan Wang;Aaksha Meghawat;Louis-Philippe Morency;E. Xing
中科院分区：
文献类型：
--
作者：
Haohan Wang;Aaksha Meghawat;Louis-Philippe Morency;E. Xing
最近，多模态情感分析受到越来越多的关注。它可以在视频评论和调查中挖掘意见，这些意见现在在YouTube等在线平台上比比皆是。然而，高质量的多模态情绪数据样本数量有限，可能会引入情绪依赖于数据集中单个特定特征的问题。这导致训练模型在更大的在线平台上缺乏分类的泛化性。在本文中，我们首先对数据进行检验，并验证了这种依赖问题的存在性。然后，我们提出了一种选择加性学习（SAL）过程，提高了训练好的判别神经网络的泛化能力。SAL是一种两阶段学习方法。在选择阶段，选择混杂学习表征。在附加阶段，它通过添加高斯噪声来强制分类器丢弃混淆的表示。在我们的实验中，我们展示了SAL如何提高最先进模型的可泛化性。我们在所有三种模式（文本、音频、视频）以及它们的融合中显著提高了预测精度。我们展示了即使在一个数据集上训练，SAL如何在测试数据集上获得良好的准确性。
Multimodal sentiment analysis is drawing an increasing amount of attention these days. It enables mining of opinions in video reviews and surveys which are now available aplenty on online platforms like YouTube. However, the limited number of high-quality multimodal sentiment data samples may introduce the problem of the sentiment being dependent on the individual specific features in the dataset. This results in a lack of generalizability of the trained models for classification on larger online platforms. In this paper, we first examine the data and verify the existence of this dependence problem. Then we propose a Select-Additive Learning (SAL) procedure that improves the generalizability of trained discriminative neural networks. SAL is a two-phase learning method. In Selection phase, it selects the confounding learned representation. In Addition phase, it forces the classifier to discard confounded representations by adding Gaussian noise. In our experiments, we show how SAL improves the generalizability of state-of-the-art models. We increase prediction accuracy significantly in all three modalities (text, audio, video), as well as in their fusion. We show how SAL, even when trained on one dataset, achieves good accuracy across test datasets.