@InProceedings{xing-zhu-zhang:2018:C18-1,
  author    = {Xing, Junjie  and  Zhu, Kenny  and  Zhang, Shaodian},
  title     = {Adaptive Multi-Task Transfer Learning for Chinese Word Segmentation in Medical Text},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  month     = {August},
  year      = {2018},
  address   = {Santa Fe, New Mexico, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {3619--3630},
  abstract  = {Chinese word segmentation (CWS) trained from open source corpus faces dramatic performance drop when dealing with domain text, especially for a domain with lots of special terms and diverse writing styles, such as the biomedical domain. However, building domain-specific CWS requires extremely high annotation cost. In this paper, we propose an approach by exploiting domain-invariant knowledge from high resource to low resource domains. Extensive experiments show that our model achieves consistently higher accuracy than the single-task CWS and other transfer learning baselines, especially when there is a large disparity between source and target domains.},
  url       = {http://www.aclweb.org/anthology/C18-1307}
}