科研成果详情

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/eISSN1041-4347 ; 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
DOI10.1109/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
被引频次:15[WOS]   [WOS记录]     [WOS相关记录]
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。
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Zhang, Xinsong]的文章
[Liu, Tianyi]的文章
[Li, Pengshuai]的文章
百度学术
百度学术中相似的文章
[Zhang, Xinsong]的文章
[Liu, Tianyi]的文章
[Li, Pengshuai]的文章
必应学术
必应学术中相似的文章
[Zhang, Xinsong]的文章
[Liu, Tianyi]的文章
[Li, Pengshuai]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。