@inproceedings{bao-etal-2017-neural,
    title = "Neural Regularized Domain Adaptation for {C}hinese Word Segmentation",
    author = "Bao, Zuyi  and
      Li, Si  and
      Xu, Weiran  and
      Gao, Sheng",
    editor = "Zhang, Yue  and
      Sui, Zhifang",
    booktitle = "Proceedings of the 9th {SIGHAN} Workshop on {C}hinese Language Processing",
    month = dec,
    year = "2017",
    address = "Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W17-6002",
    pages = "11--20",
    abstract = "For Chinese word segmentation, the large-scale annotated corpora mainly focus on newswire and only a handful of annotated data is available in other domains such as patents and literature. Considering the limited amount of annotated target domain data, it is a challenge for segmenters to learn domain-specific information while avoid getting over-fitted at the same time. In this paper, we propose a neural regularized domain adaptation method for Chinese word segmentation. The teacher networks trained in source domain are employed to regularize the training process of the student network by preserving the general knowledge. In the experiments, our neural regularized domain adaptation method achieves a better performance comparing to previous methods.",
}