資料增益（Data Augmentation）在許多研究領域中都顯示對於模型預測的準確率有幫助，然而在自然語言處理中，資料增益方式大多都具隨機性，或者在增益前需要許多語言的先備知識，因此本研究提出以注意力機制作為輔助的資料增益方法，以進行資料增益，探討注意力機制對於文本分類中的資料增益是否有影響。最後在實驗結果中證實本研究提出之方法，可有效提升分類器在分類上之準確度，在僅有500筆資料量下提升分類器10%的分類準確度。;Data augmentation is a strategy to increase the quantity of the data, in order to improve the performance of the model. This strategy is widely used in natural language processing field, however, data augmentation strategies in natural language field nowadays, either consist of a lot of randomness, or require a lot of human pre-defined rules. In our work, we propose a novel approach to augment the data according to the attention weight, which doesn’t require any human pre-defined rules yet can get rid of the randomness. Our approach increases the accuracy of the classifier model, and it shows the feasibility of taking attention weight as a basis to perform data augmentation.
