A Common Case of Jekyll and Hyde: The Synergistic Effect of Using Divided Source Training Data for Feature Augmentation

Feature augmentation is a well-known method for domain adaptation and has been shown to be effective when tested on several NLP tasks (Daume III, 2007). However, a limitation of the method is that it requires labeled data from the target domain and very often such data is unavailable. In this paper, we propose to use training data selection to divide the source domain training data into two parts, pseudo target data (the selected part) and source data (the unselected part), and then apply feature augmentation on the two parts of the training data. This approach has two advantages: first, feature augmentation can be applied even when there is no labeled data from the target domain; second, the approach can take advantage of all the training data including the part that is not selected by training data selection. We evaluate the approach on Chinese word segmentation and part-of-speech tagging and show that it outperforms the baseline where no feature augmentation is applied.