Distant supervision for neural relation extraction integrated with word attention and property features
Distant supervision for neural relation extraction integrated with word attention and property features
复制标题
结合词注意力和属性特征的神经关系提取的远程监督
DOI：
10.1016/j.neunet.2018.01.006
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Li Ximing
中科院分区：
文献类型：
--
作者：
Qu Jianfeng;Ouyang Dantong;Hua Wen;Ye Yuxin;Li Ximing
Distant supervision for neural relation extraction is an efficient approach to extracting massive relations with reference to plain texts. However, the existing neural methods fail to capture the critical words in sentence encoding and meanwhile lack useful sentence information for some positive training instances. To address the above issues, we propose a novel neural relation extraction model. First, we develop a word-level attention mechanism to distinguish the importance of each individual word in a sentence, increasing the attention weights for those critical words. Second, we investigate the semantic information from word embeddings of target entities, which can be developed as a supplementary feature for the extractor. Experimental results show that our model outperforms previous state-of-the-art baselines.
登录
查看更多内容
DOI：
10.3115/1219840.1219892
发表时间：
2005-06
期刊：
--
影响因子：
--
作者：
Shubin Zhao;R. Grishman
通讯作者：
Shubin Zhao;R. Grishman
DOI：
10.3115/v1/p15-1128
发表时间：
2015-07
期刊：
--
影响因子：
--
作者：
Wen-tau Yih;Ming-Wei Chang;Xiaodong He;Jianfeng Gao
通讯作者：
Wen-tau Yih;Ming-Wei Chang;Xiaodong He;Jianfeng Gao
DOI：
10.1145/1807085.1807097
发表时间：
2010-06
期刊：
Proceedings of the twenty-ninth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
影响因子：
--
作者：
G. Weikum;M. Theobald
通讯作者：
G. Weikum;M. Theobald
DOI：
10.18653/v1/p16-1105
发表时间：
2016-01
期刊：
ArXiv
影响因子：
--
作者：
Makoto Miwa;Mohit Bansal
通讯作者：
Makoto Miwa;Mohit Bansal
DOI：
10.1162/tacl_a_00234
发表时间：
2013-10
影响因子：
10.9
作者：
Alan Ritter;Luke Zettlemoyer;Mausam;Oren Etzioni
通讯作者：
Alan Ritter;Luke Zettlemoyer;Mausam;Oren Etzioni