Knowledge Commons of Institute of Automation,CAS
A Novel End2End Multiple Tagging Model for Knowledge Extraction | |
Yuanhua Song1,2; Hongyun Bao1![]() ![]() | |
2019-07-14 | |
会议名称 | IJCNN 2019 |
会议日期 | 2019-7-14 |
会议地点 | Budapest, Hungary |
摘要 | It is an emerging research topic in NLP to joint extraction of knowledge including entities and relations from unstructured text and representing them as meaningful triplets. Despite significant progresses made by recent deep neural network based solutions, these methods still confront the overlapping issue that different relational triplets may have overlapped entities in a sentence, and it is troublesome to address this issue by current solutions. In this paper, we propose a novel end2end multiple tagging model to address the overlapping issue and extract knowledge from unstructured text. Specifically, we devise a multiple tagging scheme that transforms the problem of joint entity and relation extraction into a multiple sequence tagging problem. By using GRU as the building block for encoding-decoding, the proposed model is capable of handling the triplet overlapping problem because the decoder layer allows one entity to take part in more than one triplet. The whole network is end2end trainable and outputs all triplets in a sentence directly. Experimental results on the NYT and KBP benchmarks demonstrate that the proposed model significantly improves the recall of triplet, and consequently, achieving the new state-of-the-art in the task of triplet extraction. |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
收录类别 | EI |
七大方向——子方向分类 | 知识表示与推理 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/26137 |
专题 | 复杂系统认知与决策实验室_听觉模型与认知计算 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences Beijing, China 2.Xiangtan University |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yuanhua Song,Hongyun Bao,Zhineng Chen,et al. A Novel End2End Multiple Tagging Model for Knowledge Extraction[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
N-20164.pdf(937KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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