亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

LENA: Locality-Expanded Neural Embedding for Knowledge Base Completion

作者
Fanshuang Kong,Richong Zhang,Yongyi Mao,Ting Deng
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence [Association for the Advancement of Artificial Intelligence]
卷期号:33 (01): 2895-2902 被引量:5
标识
DOI:10.1609/aaai.v33i01.33012895
摘要

Embedding based models for knowledge base completion have demonstrated great successes and attracted significant research interest. In this work, we observe that existing embedding models all have their loss functions decomposed into atomic loss functions, each on a triple or an postulated edge in the knowledge graph. Such an approach essentially implies that conditioned on the embeddings of the triple, whether the triple is factual is independent of the structure of the knowledge graph. Although arguably the embeddings of the entities and relation in the triple contain certain structural information of the knowledge base, we believe that the global information contained in the embeddings of the triple can be insufficient and such an assumption is overly optimistic in heterogeneous knowledge bases. Motivated by this understanding, in this work we propose a new embedding model in which we discard the assumption that the embeddings of the entities and relation in a triple is a sufficient statistic for the triple’s factual existence. More specifically, the proposed model assumes that whether a triple is factual depends not only on the embedding of the triple but also on the embeddings of the entities and relations in a larger graph neighbourhood. In this model, attention mechanisms are constructed to select the relevant information in the graph neighbourhood so that irrelevant signals in the neighbourhood are suppressed. Termed locality-expanded neural embedding with attention (LENA), this model is tested on four standard datasets and compared with several stateof-the-art models for knowledge base completion. Extensive experiments suggest that LENA outperforms the existing models in virtually every metric.

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
高高的网络完成签到,获得积分10
2秒前
哇咔咔完成签到,获得积分10
2秒前
null的应助被科研通管家采纳,获得10
3秒前
null的应助被科研通管家采纳,获得10
3秒前
嘻嘻哈哈的应助被科研通管家采纳,获得10
4秒前
嘻嘻哈哈的应助被科研通管家采纳,获得10
4秒前
华仔的应助被科研通管家采纳,获得10
4秒前
天天快乐的应助被科研通管家采纳,获得10
4秒前
4秒前
10秒前
yinh完成签到 ,获得积分10
10秒前
乐观小蕊完成签到 ,获得积分10
10秒前
369ninja发布了新的文献求助10
10秒前
Cupid完成签到,获得积分10
16秒前
洪亮发布了新的文献求助30
16秒前
17秒前
20秒前
159357发布了新的文献求助30
21秒前
可爱馒头完成签到,获得积分10
21秒前
21秒前
23秒前
传奇3的应助被Flynn采纳,获得10
24秒前
yangzai完成签到 ,获得积分0
25秒前
26秒前
李华完成签到,获得积分10
27秒前
27秒前
欣喜的若山完成签到 ,获得积分10
27秒前
黄天完成签到 ,获得积分10
28秒前
小叶子完成签到 ,获得积分10
29秒前
llqq完成签到,获得积分10
29秒前
洪亮完成签到,获得积分10
30秒前
李华发布了新的文献求助10
31秒前
32秒前
32秒前
32秒前
林诗萍完成签到 ,获得积分10
33秒前
Flynn发布了新的文献求助10
37秒前
清汐完成签到 ,获得积分10
37秒前
阿腾发布了新的文献求助10
38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
Grapes 1000
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
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 8179656
求助须知:如何正确求助?哪些是违规求助? 9569921
关于积分的说明 21807706
捐赠科研通 7775141
什么是DOI,文献DOI怎么找? 3433072
关于科研通互助平台的介绍 2557032
邀请新用户注册赠送积分活动 2478778