Incorporating Deep Syntactic and Semantic Knowledge for Chinese Sequence Labeling with GCN
This work addresses Chinese sequence labeling tasks, which is incremental as it builds on existing methods by integrating structural information.
The paper tackled the problem of Chinese sequence labeling by incorporating syntactic and semantic knowledge using graph convolutional networks, resulting in improved performance on five benchmark datasets for tasks like word segmentation and part-of-speech tagging.
Recently, it is quite common to integrate Chinese sequence labeling results to enhance syntactic and semantic parsing. However, little attention has been paid to the utility of hierarchy and structure information encoded in syntactic and semantic features for Chinese sequence labeling tasks. In this paper, we propose a novel framework to encode syntactic structure features and semantic information for Chinese sequence labeling tasks with graph convolutional networks (GCN). Experiments on five benchmark datasets, including Chinese word segmentation and part-of-speech tagging, demonstrate that our model can effectively improve the performance of Chinese labeling tasks.