Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Distant Supervision
This work addresses data scarcity for researchers studying ancient Chinese linguistics, but it is incremental as it builds on existing distant supervision techniques with a refinement step.
The paper tackles the problem of limited annotated data for ancient Chinese word segmentation and part-of-speech tagging by proposing a distant supervision method with a relabeling step using deep neural networks, resulting in a model that outperforms baseline methods trained on distant supervision or annotated data alone.
Ancient Chinese word segmentation (WSG) and part-of-speech tagging (POS) are important to study ancient Chinese, but the amount of ancient Chinese WSG and POS tagging data is still rare. In this paper, we propose a novel augmentation method of ancient Chinese WSG and POS tagging data using distant supervision over parallel corpus. However, there are still mislabeled and unlabeled ancient Chinese words inevitably in distant supervision. To address this problem, we take advantage of the memorization effects of deep neural networks and a small amount of annotated data to get a model with much knowledge and a little noise, and then we use this model to relabel the ancient Chinese sentences in parallel corpus. Experiments show that the model trained over the relabeled data outperforms the model trained over the data generated from distant supervision and the annotated data. Our code is available at https://github.com/farlit/ACDS.