Multimodal sentiment analysis has recently gained popularity because of its
relevance to social media posts, customer service calls and video blogs. In
this paper, we address three aspects of multimodal sentiment analysis; 1. Cross
modal interaction learning, i.e. how multiple modalities contribute to the
sentiment, 2. Learning long-term dependencies in multimodal interactions and 3.
Fusion of unimodal and cross modal cues. Out of these three, we find that
learning cross modal interactions is beneficial for this problem. We perform
experiments on two benchmark datasets, CMU Multimodal Opinion level Sentiment
Intensity (CMU-MOSI) and CMU Multimodal Opinion Sentiment and Emotion Intensity
(CMU-MOSEI) corpus. Our approach on both these tasks yields accuracies of 83.9%
and 81.1% respectively, which is 1.6% and 1.34% absolute improvement over
current state-of-the-art.

本文讨论了多模态情感分析的三个方面：跨模态交互学习、多模态交互中的长期依赖性学习和一元和跨模态线索的融合，发现学习跨模态交互对解决该问题很有益。在两个基准数据集（CMU-MOSI 和 CMU-MOSEI 语料库）上进行实验，取得了 83.9％和 81.1％的准确率，分别比当前最先进技术提高了 1.6％和 1.34％的绝对精度。