多模态知识表示系列——ConvKB模型学习

A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network

NAACL-2018

---

Reference format：

GB/T7714：
Nguyen D Q , Nguyen T D , Nguyen D Q , et al. A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network[C]// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018.

Datasets：

WN18RR、FB15k-237

Problems：

ConvE focus on the local relationships among different dimensional entries in each of v_h or v_r.
Does not observe the global relationsships among the dimensional enties of an triple (includes v_t).
Ignores the transitional characteristic in transition-based models, which is one of the most useful intutions for the task.

Score Function：

其中Ω与W共享参数

Loss Function:

Experiments：

Datasets	MR	MRR	Hits@10
FB15k-237	257	0.396	51.7
WN18RR	2554	0.248	52.5

---

可参考点：

1、为什么不使用数据量更大的FB15k与WN18？
答：FB15k与WN18包含了很多可逆关系，比如<A, is_a_friend_of ,B>，这类关系很容易逆向推出<B, is_a_friend_of, A>，对该类关系进行剔除后生成FB15K-237与WN18RR。

2、简单修改Baseline的计算方法也许可以取得较好的结果。

3、不同的负采样方法存在一定的优劣性，本文采用的是Bernoulli trick。

---

原文PDF与开源代码已上传