Distant supervision for relation extraction with hierarchical attention-based networks

判决 计算机科学 关系抽取 特征(语言学) 人工智能 噪音(视频) 关系(数据库) 代表(政治) 自然语言处理 文字袋模型 机器学习 模式识别(心理学) 信息抽取 数据挖掘 哲学 法学 图像(数学) 政治 语言学 政治学
作者
Jing Zhang,Meilin Cao
出处
期刊:Expert Systems With Applications [Elsevier BV]
卷期号:220: 119727-119727 被引量:6
标识
DOI:10.1016/j.eswa.2023.119727
摘要

Distant supervision employs external knowledge bases to automatically label corpora. The labeled sentences in a corpus are usually packaged and trained for relation extraction using a multi-instance learning paradigm. The automated distant supervision inevitably introduces label noises. Previous studies that used sentence-level attention mechanisms to de-noise neither considered correlation among sentences in a bag nor correlation among bags. As a result, a large amount of effective supervision information is lost, which will affect the performance of learned relation extraction models. Moreover, these methods ignore the lack of feature information in the few-sentence bags (especially the one-sentence bags). To address these issues, this paper proposes hierarchical attention-based networks that can de-noise at both sentence and bag levels. In the calculation of bag representation, we provide weights to sentence representations using sentence-level attention that considers correlations among sentences in each bag. Then, we employ bag-level attention to combine the similar bags by considering their correlations, which can enhance the feature of target bags with poor feature information, and to provide properer weights in the calculation of bag group representation. Both sentence-level attention and bag-level attention can make full use of supervised information to improve model performance. The proposed method was compared with nine state-of-the-art methods on the New York Times datasets and Google IISc Distant Supervision dataset, respectively, whose experimental results show its conspicuous advantages in relation extraction tasks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
abc发布了新的文献求助10
1秒前
2秒前
yuzej发布了新的文献求助10
2秒前
2秒前
WANG完成签到,获得积分10
3秒前
3秒前
4秒前
4秒前
英俊小鼠完成签到,获得积分10
4秒前
田様应助Yuan88采纳,获得10
5秒前
syangZ完成签到,获得积分10
6秒前
7秒前
汉堡包应助cm采纳,获得10
8秒前
KOIKOI完成签到,获得积分10
8秒前
9秒前
雪山飞龙发布了新的文献求助10
9秒前
呆萌冷风发布了新的文献求助10
10秒前
888发布了新的文献求助10
11秒前
Clare发布了新的文献求助10
11秒前
13秒前
不敢自称科研人完成签到,获得积分10
13秒前
13秒前
qq发布了新的文献求助10
14秒前
星星发布了新的文献求助10
14秒前
15秒前
chocho完成签到,获得积分10
16秒前
bingbing完成签到,获得积分10
17秒前
呆萌冷风完成签到,获得积分10
18秒前
Yuan88发布了新的文献求助10
18秒前
20秒前
21秒前
索浩鑫发布了新的文献求助10
22秒前
传奇3应助bingbing采纳,获得10
24秒前
24秒前
26秒前
26秒前
27秒前
Clare完成签到,获得积分10
27秒前
888完成签到,获得积分10
29秒前
搜集达人应助清新的Q采纳,获得10
29秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969884
求助须知:如何正确求助?哪些是违规求助? 3514604
关于积分的说明 11174901
捐赠科研通 3249928
什么是DOI,文献DOI怎么找? 1795149
邀请新用户注册赠送积分活动 875599
科研通“疑难数据库(出版商)”最低求助积分说明 804891