KGGen: A Generative Approach for Incipient Knowledge Graph Population

计算机科学 注释 判别式 图形 人工智能 生成语法 人口 生成模型 自然语言处理 知识图 任务(项目管理) 情报检索 机器学习 理论计算机科学 人口学 管理 社会学 经济
作者
Hao Chen,Chenwei Zhang,Jun Li,Philip S. Yu,Ning Jing
出处
期刊:IEEE Transactions on Knowledge and Data Engineering [IEEE Computer Society]
卷期号:34 (5): 2254-2267 被引量:6
标识
DOI:10.1109/tkde.2020.3014166
摘要

Knowledge graph is becoming an indispensable resource that offers structured information for numerous AI applications. However, the knowledge graph often suffers from its incompleteness. Building a complete, high-quality knowledge graph is time-consuming and requires significant human annotation efforts. In this paper, we study the Knowledge Graph Population task, which aims at extending the scale of structured knowledge, with a special focus on reducing data preparation and annotation efforts. Previous works mainly based on discriminative methods build classifiers and verify candidate triplets that are extracted from texts, which heavily rely on the quality of data collection and co-occurrance of entities in the text. However, such methods fail to generalize on entity pairs that are not highly co-occurred, and fail to discover entity pairs that are not co-occurred at all in the given text corpus. We introduce a generative perspective to approach this task and define each relationship by learning the data distribution that embodies the core common properties for relational reasoning. A generative model KGGen is proposed, which samples from the learned data distribution for each relation and can generate triplets regardless of entity pair co-occurrence in the text corpus. To further improve the generation quality while alleviate human annotation efforts, adversarial learning is adopted to not only encourage generating high quality triplets, but also give model the ability to automatically assess the generation quality. Quantitative and qualitative experimental results conducted on two real-world generic knowledge graphs show that the proposed model KGGen generates novel and meaningful triplets with improved efficiency and less human annotation comparing with the state-of-the-art approaches.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
1秒前
丘比特的应助被兮云采纳,获得10
1秒前
1秒前
朝闻道完成签到 ,获得积分10
1秒前
慕青的应助被滕侑林采纳,获得10
2秒前
ivy完成签到,获得积分10
2秒前
wang完成签到,获得积分10
2秒前
诚心的松思完成签到,获得积分10
2秒前
3秒前
风格化橙发布了新的文献求助10
3秒前
3秒前
Akim的应助被zz采纳,获得10
4秒前
勤奋一一发布了新的文献求助10
4秒前
bkagyin的应助被机灵的含卉采纳,获得10
4秒前
余香的应助被初初初啊采纳,获得20
5秒前
英姑的应助被段段采纳,获得10
6秒前
6秒前
斯文败类的应助被调皮的雨筠采纳,获得10
6秒前
11完成签到,获得积分10
7秒前
宇宙星河完成签到,获得积分10
7秒前
7秒前
pure完成签到 ,获得积分10
7秒前
小马甲的应助被jx314采纳,获得10
8秒前
初景发布了新的文献求助30
8秒前
Jasper的应助被xxtdger采纳,获得10
8秒前
嘻嘻嘻完成签到,获得积分10
9秒前
summer发布了新的文献求助10
10秒前
10秒前
fan的应助被完美的紊采纳,获得10
10秒前
10秒前
feiyan发布了新的文献求助10
11秒前
molihuakai的应助被blhh采纳,获得10
11秒前
浮生若梦发布了新的文献求助10
11秒前
zhanglh发布了新的文献求助50
12秒前
12秒前
结实的秋天完成签到,获得积分20
12秒前
狂野的小熊猫完成签到,获得积分10
13秒前
科研通AI6.4的应助被packcoat采纳,获得10
13秒前
深情安青的应助被Liu采纳,获得10
13秒前
初景的应助被无奈的映阳采纳,获得20
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8171932
求助须知:如何正确求助?哪些是违规求助? 9564633
关于积分的说明 21775854
捐赠科研通 7763499
什么是DOI,文献DOI怎么找? 3431053
关于科研通互助平台的介绍 2554930
邀请新用户注册赠送积分活动 2476076