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 => Position Selective Attention => 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.- Anthology ID:
- 2020.socialnlp-1.7
- Volume:
- Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Lun-Wei Ku, Cheng-Te Li
- Venue:
- SocialNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 51–60
- Language:
- URL:
- https://aclanthology.org/2020.socialnlp-1.7
- DOI:
- 10.18653/v1/2020.socialnlp-1.7
- Cite (ACL):
- Shengbin Jia, Ling Ding, Xiaojun Chen, Shijia E, and Yang Xiang. 2020. Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text. In Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media, pages 51–60, Online. Association for Computational Linguistics.
- Cite (Informal):
- Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text (Jia et al., SocialNLP 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.socialnlp-1.7.pdf
- Data
- Weibo NER