The surge of social media use has triggered huge demands of multilingual sentiment analysis (MSA) for various purposes, such as unveiling cultural difference. So far, traditional methods resorted to machine translation (MT)-translating other languages to English, then adopted the existing methods of English. However, this paradigm is highly conditioned by the quality of MT. In this paper, we propose a new deep learning paradigm for MSA that assimilates the differences between languages. First, separately pre-trained monolingual word embeddings in different spaces are mapped into a shared embedding space; then, a parameter-sharing deep neural network using those mapped word embeddings for MSA is built. The experimental results justify the effectiveness of the proposed paradigm. Especially, our convolutional neural network (CNN) model with orthogonally mapped word embeddings outperforms a state-of-the-art baseline by 3.4% in terms of classification accuracy.
展开▼
机译：社交媒体使用的激增引发了多语种情感分析（MSA）的巨大需求，以各种目的，如揭幕文化差异。到目前为止，传统方法采用机器翻译（MT） - 将其他语言到英语，然后采用现有的英语方法。然而，这种范式受到Mt的质量的高度调节。在本文中，我们为MSA提出了一种新的深度学习范式，可以吸收语言之间的差异。首先，在不同空格中单独进行预先培训的单声道单词嵌入在共享嵌入空间中;然后，建立使用这些映射的Word Embeddings for MSA的参数共享深神经网络。实验结果证明了拟议范式的有效性。特别是，我们的卷积神经网络（CNN）模型具有正交映射的Word Embeddings在分类准确性方面优于最先进的基线3.4％。
展开▼
