Paper points

该论文用NTN（Neural tensor networks）进行知识库中嵌入对象（Embedding）之间关系（Relation）的学习和预测（完善）。主要考虑了3个重要思路。

Neural tensor networks

Triple（e₁， R， e₂）， which means relation R keeps between e1 and e2. Model built to score the existing triples high and score negative samples low. Score function in this paper is constructed as a bilinear one, which consists of e₁*M* e₂, V*[e₁, e₂]^t, b.
In my opinion, e₁* M * e₂ represents inter-operations, V*[e₁, e₂]’ represents linear combination, b is bias, where M, V and b are parameters of the model for specific relation.
Loss function is constructed as contrastive max-marginal distance. For existing(positive) triple (e₁, R, e₂), randomly sample e1 or e2 to be replaced with some randomly chosen entity e’ to form negative relation(e, R, e^’) , then loss can be defined as
max(0, 1 - (g(e₁, R, e₂) - g(e, R, e^’))) plus L2-regularization. g is the score function.

Entity embedding AS average word embeddings

The combination of word information utilizes semantical information, which is useful to mine underlying text as new information sources.
It improves model performance more than NTN model does.

Pretrained word embedding vectors used in initialization

Pre-trained word embeddings as initialization, incorporates large scale corpus distributions, make results even better.

Conclusion

Information sources are important for models, not necessarily new ones, sometimes the ignored ones.

Vector relations can be modeled as inter-operations as bilinear functions, or as traditionally linear combinations. This can be understood as variable multiplication and summation ops.

Contrastive max-margin is a often-used loss function construction method for non-probabilistic problems

Negative sampling is widely used to construct negative samples

Word embeddings are import information sources for KB-like text based applications.

论文记录：Reasoning with neural tensor networks for Knowledge Base completion相关推荐

【阅读笔记】Reasoning With Neural Tensor Networks for Knowledge Base Completion
前言论文地址 Poster Abstract 这篇论文里,作者介绍了一个适用于推理两个实体关系的神经网络(Neural Tensor Network).相比之前的工作要么将实体表示成离散的最小单元或 ...
论文解读：Improved Neural Relation Detection for Knowledge Base Question Answering
论文解读:Improved Neural Relation Detection for Knowledge Base Question Answering 本文解决KBQA中的子问题--Relat ...
关于GCN的论文笔记--End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
用于知识图谱完成的端到端结构感知卷积网络论文题目 End-to-end Structure-Aware Convolutional Networks for Knowledge Base Compl ...
【阅读笔记】：End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
为解决知识图谱(KG)中三元组不完整问题,本文结合加权图卷积神经网络(WGCN)和Conv-TransE两个模块,提出了SACN(Structure-Aware Convolutional Netwo ...
End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
研究问题将图网络作为编码器,将Conv-TransE作为解码器,应用于知识图谱补全任务背景动机 ConvE模型在做卷积之前对embedding实施了reshape操作,并且没有保留TransE系列 ...
论文翻译：《Improved Neural Relation Detection for Knowledge Base Question Answering》
该论文于2017年发表在ACL,主要讲了智能问答在sq和wq两个数据集上的性能提升,本人研究生方向为这个,故翻译此论文,希望对大家有用. 论文地址:Improved Neural Relation D ...
Improved Neural Relation Detection for Knowledge Base Question Answering
Improved Neural Relation Detection for Knowledge Base Question Answering 2017 ACL SQ78.7 WebQSP63.9 ...
论文浅尝 - ESWC2020 | YAGO 4: A Reason-able Knowledge Base
论文笔记整理:叶群,浙江大学计算机学院,知识图谱.NLP方向. 会议:ESWC 2020 链接:https://suchanek.name/work/publications/eswc-2020-ya ...
ConvKB代码：A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
1 介绍本篇论文以卷积的方式对知识图谱进行补全,其方法采用CNN的形式进行知识图谱补全,将三元组统一处理,进行评估,评估出得分最高的一组,该方法在论文ConvE的基础上进行改进,其在逻辑实现的过程中 ...

论文记录：Reasoning with neural tensor networks for Knowledge Base completion