@inproceedings{jia-etal-2020-incorporating,
    title = "Incorporating Uncertain Segmentation Information into {C}hinese {NER} for Social Media Text",
    author = "Jia, Shengbin  and
      Ding, Ling  and
      Chen, Xiaojun  and
      E, Shijia  and
      Xiang, Yang",
    editor = "Ku, Lun-Wei  and
      Li, Cheng-Te",
    booktitle = "Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.socialnlp-1.7/",
    doi = "10.18653/v1/2020.socialnlp-1.7",
    pages = "51--60",
    abstract = "Chinese word segmentation is necessary to provide word-level information for Chinese named entity recognition (NER) systems. However, segmentation error propagation is a challenge for Chinese NER while processing colloquial data like social media text. In this paper, we propose a model (UIcwsNN) that specializes in identifying entities from Chinese social media text, especially by leveraging uncertain information of word segmentation. Such ambiguous information contains all the potential segmentation states of a sentence that provides a channel for the model to infer deep word-level characteristics. We propose a trilogy (i.e., Candidate Position Embedding ={\ensuremath{>}} Position Selective Attention ={\ensuremath{>}} Adaptive Word Convolution) to encode uncertain word segmentation information and acquire appropriate word-level representation. Experimental results on the social media corpus show that our model alleviates the segmentation error cascading trouble effectively, and achieves a significant performance improvement of 2{\%} over previous state-of-the-art methods."
}