Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism | |
Cao, Pengfei; Chen, Yubo![]() ![]() ![]() | |
2018 | |
会议日期 | Oct 31, 2018 - Nov 4, 2018 |
会议地点 | Brussels, Belgium |
英文摘要 | amed entity recognition (NER) is an important task in natural language processing area, which needs to determine entities boundaries and classify them into pre-defined categories. For Chinese NER task, there is only a very small amount of annotated data available. Chinese NER task and Chinese word segmentation (CWS) task have many similar word boundaries. There are also specificities in each task. However, existing methods for Chinese NER either do not exploit word boundary information from CWS or cannot filter the specific information of CWS. In this paper, we propose a novel adversarial transfer learning framework to make full use of task-shared boundaries information and prevent the taskspecific features of CWS. Besides, since arbitrary character can provide important cues when predicting entity type, we exploit selfattention to explicitly capture long range dependencies between two tokens. Experimental results on two different widely used datasets show that our proposed model significantly and consistently outperforms other state-ofthe- art methods. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/26131] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_自然语言处理团队 |
作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Cao, Pengfei,Chen, Yubo,Liu, Kang,et al. Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism[C]. 见:. Brussels, Belgium. Oct 31, 2018 - Nov 4, 2018. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论