发表状态 | 已发表Published |
题名 | Robust Neural Relation Extraction via Multi-Granularity Noises Reduction |
作者 | |
发表日期 | 2021-09 |
发表期刊 | IEEE Transactions on Knowledge and Data Engineering
![]() |
ISSN/eISSN | 1041-4347 ; 1558-2191 |
卷号 | 33期号:9页码:3297 - 3310 |
摘要 | Distant supervision is widely used to extract relational facts with automatically labeled datasets to reduce high cost of human annotation. However, current distantly supervised methods suffer from the common problems of word-level and sentence-level noises, which come from a large proportion of irrelevant words in a sentence and inaccurate relation labels for numerous sentences. The problems lead to unacceptable precision in relation extraction and are critical for the success of using distant supervision. In this paper, we propose a novel and robust neural approach to deal with both problems by reducing influences of the multi-granularity noises. Three levels of noises from word, sentence until knowledge type are carefully considered in this work. We first initiate a question-answering based relation extractor (QARE) to remove noisy words in a sentence. Then we use multi-focus multi-instance learning (MMIL) to alleviate the effects of sentence-level noise by utilizing wrongly labeled sentences properly. Finally, to enhance our method against all the noises, we initialize parameters in our method with a priori knowledge learned from the relevant task of entity type classification by transfer learning. Extensive experiments on both existing benchmark and an improved larger dataset demonstrate that our proposed approach remarkably achieves new state-of-the-art performance. |
关键词 | distant supervision multi-instance learning Neural relation extraction transfer learning |
DOI | 10.1109/TKDE.2020.2964747 |
URL | 查看来源 |
收录类别 | SCIE |
语种 | 英语English |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000682116800011 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | https://repository.uic.edu.cn/handle/39GCC9TT/5354 |
专题 | 个人在本单位外知识产出 |
作者单位 | 1.ByteDance Ai Lab, Shanghai, China 2.Department of Computer and Information Science, Shanghai Jiao Tong University, Shanghai, 410083, China 3.State Key Lab of IoT for Smart City, University of Macau, Taipa, Macau, China |
推荐引用方式 GB/T 7714 | Zhang, Xinsong,Liu, Tianyi,Li, Pengshuaiet al. Robust Neural Relation Extraction via Multi-Granularity Noises Reduction[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 33(9): 3297 - 3310. |
APA | Zhang, Xinsong, Liu, Tianyi, Li, Pengshuai, Jia, Weijia, & Zhao, Hai. (2021). Robust Neural Relation Extraction via Multi-Granularity Noises Reduction. IEEE Transactions on Knowledge and Data Engineering, 33(9), 3297 - 3310. |
MLA | Zhang, Xinsong,et al."Robust Neural Relation Extraction via Multi-Granularity Noises Reduction". IEEE Transactions on Knowledge and Data Engineering 33.9(2021): 3297 - 3310. |
条目包含的文件 | 条目无相关文件。 |
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