Transfer Deep Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network
This work addresses the challenge of insufficient training data for Chinese word segmentation in low-resource settings, representing an incremental improvement over existing neural network methods.
The paper tackles the problem of low-resource Chinese word segmentation by proposing a transfer learning method that leverages high-resource corpora, achieving state-of-the-art F-scores of 96.1% and 96.2% on PKU and CTB datasets with improvements of 2.3% and 1.5% respectively.
Recent studies have shown effectiveness in using neural networks for Chinese word segmentation. However, these models rely on large-scale data and are less effective for low-resource datasets because of insufficient training data. We propose a transfer learning method to improve low-resource word segmentation by leveraging high-resource corpora. First, we train a teacher model on high-resource corpora and then use the learned knowledge to initialize a student model. Second, a weighted data similarity method is proposed to train the student model on low-resource data. Experiment results show that our work significantly improves the performance on low-resource datasets: 2.3% and 1.5% F-score on PKU and CTB datasets. Furthermore, this paper achieves state-of-the-art results: 96.1%, and 96.2% F-score on PKU and CTB datasets.