2020/04/14 by Shengbin Jia, Ling Ding, Jia, Shengbin +7
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text and Document Classification Technologies #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2004.06384
openalex publication_date 2020/04/14 · openalex created_date 2020/04/24 · openalex updated_date 2026/07/28
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 ambiguous information of word segmentation. Such uncertain 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 -> position selective attention -> adaptive word convolution) to encode uncertain word segmentation information and acquire appropriate word-level representation. Experiments results on the social media corpus show that our model alleviates the segmentation error cascading trouble effectively, and achieves a significant performance improvement of more than 2% over previous state-of-the-art methods.