Shengbin Jia author Ling Ding author Xiaojun Chen author Shijia E author Yang Xiang author 2020-jul text Association for Computational Linguistics Online conference publication 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 =\textgreater Position Selective Attention =\textgreater 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. jia-etal-2020-incorporating https://www.aclweb.org/anthology/2020.socialnlp-1.7 2020-jul 51 60