论文标题
用于文档级别情感分类的体系结构的系统比较
A Systematic Comparison of Architectures for Document-Level Sentiment Classification
论文作者
论文摘要
文档由较小的作品（段落，句子和代币）组成，它们之间具有复杂的关系。考虑到这些文档中固有的结构的情感分类模型比没有的结构具有理论优势。同时，基于语言模型预处理的转移学习模型已显示出对文档分类的希望。但是，这两个范式尚未系统比较，在哪些情况下，一种方法比另一种方法更好。在这项工作中，我们从经验上比较了层次模型和转移学习文档级别分类的学习。我们表明，非平凡的分层模型优于先前的基线，并以五种语言对文档级别的情感分类进行转移学习。
Documents are composed of smaller pieces - paragraphs, sentences, and tokens - that have complex relationships between one another. Sentiment classification models that take into account the structure inherent in these documents have a theoretical advantage over those that do not. At the same time, transfer learning models based on language model pretraining have shown promise for document classification. However, these two paradigms have not been systematically compared and it is not clear under which circumstances one approach is better than the other. In this work we empirically compare hierarchical models and transfer learning for document-level sentiment classification. We show that non-trivial hierarchical models outperform previous baselines and transfer learning on document-level sentiment classification in five languages.
