A Systematic Comparison of Architectures for Document-Level Sentiment Classification
This work addresses the need for better sentiment classification methods for documents in multiple languages, though it is incremental as it compares existing paradigms.
The paper tackled the problem of comparing hierarchical models and transfer learning for document-level sentiment classification, finding that non-trivial hierarchical models outperform previous baselines and transfer learning across five languages.
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.