Cross Encoding as Augmentation: Towards Effective Educational Text Classification
This addresses the problem of automated tagging for educational content, which is incremental as it builds on existing retrieval methods with specific enhancements.
The paper tackles the data scarcity problem in educational text classification (auto-tagging) by proposing a retrieval approach called CEAA, which leverages transfer learning and data augmentation to improve performance in multi-label and low-resource scenarios, showing effectiveness compared to state-of-the-art models.
Text classification in education, usually called auto-tagging, is the automated process of assigning relevant tags to educational content, such as questions and textbooks. However, auto-tagging suffers from a data scarcity problem, which stems from two major challenges: 1) it possesses a large tag space and 2) it is multi-label. Though a retrieval approach is reportedly good at low-resource scenarios, there have been fewer efforts to directly address the data scarcity problem. To mitigate these issues, here we propose a novel retrieval approach CEAA that provides effective learning in educational text classification. Our main contributions are as follows: 1) we leverage transfer learning from question-answering datasets, and 2) we propose a simple but effective data augmentation method introducing cross-encoder style texts to a bi-encoder architecture for more efficient inference. An extensive set of experiments shows that our proposed method is effective in multi-label scenarios and low-resource tags compared to state-of-the-art models.