Unsupervised multi-granular Chinese word segmentation and term discovery via graph partition

Zheng Yuan, Yuanhao Liu, Qiuyang Yin, Boyao Li, Xiaobin Feng, Guoming Zhang, Sheng YuJ. Biomed. Informatics 2020 · OpenReview

Abstract

Highlights • State-of-the-art unsupervised word segmentation achieved by graph partition. • Multi-granular word segmentation substantially improved term discovery. • Dynamic programming was used to achieve highly efficient graph partition. • Training by simulated data can improve word segmentation and term discovery accuracy. Abstract Objective This study aims at realizing unsupervised term discovery in Chinese electronic health records (EHRs) by using the word segmentation technique. The existing supervised algorithms do not perform satisfactorily in the case of EHRs, as annotated medical data are scarce. We propose an unsupervised segmentation method (GTS) based on the graph partition principle, whose multi-granular segmentation capability can help realize efficient term discovery. Methods A sentence is converted to an undirected graph, with the edge weights based on n-gram statistics, and ratio cut is used to split the sentence into words. The graph partition is solved efficiently via dynamic programming, and multi-granularity is realized by setting different partition numbers. A BERT-based discriminator is trained using generated samples to verify the correctness of the word boundaries. The words that are not recorded in existing dictionaries are retained as potential medical terms. Results We compared the GTS approach with mature segmentation systems for both word segmentation and term discovery. MD students manually segmented Chinese EHRs at fine and coarse granularity levels and reviewed the term discovery results. The proposed unsupervised method outperformed all the competing algorithms in the word segmentation task. In term discovery, GTS outperformed the best baseline by 17 percentage points (a 47% relative percentage of increment) on F1-score. Conclusion In the absence of annotated training data, the graph partition technique can effectively use the corpus statistics and even expert knowledge to realize unsupervised word segmentation of EHRs. Multi-granular segmentation can be used to provide potential medical terms of various lengths with high accuracy.
BibTeX
@article{yuan2020unsupervised,
  author = {Zheng Yuan and Yuanhao Liu and Qiuyang Yin and Boyao Li and Xiaobin Feng and Guoming Zhang and Sheng Yu},
  title = {{Unsupervised multi-granular Chinese word segmentation and term discovery via graph partition}},
  journal = {J. Biomed. Informatics},
  year = {2020},
  url = {https://openreview.net/forum?id=11nI4z6Dkdf},
}

Loading related content...

Figure