Xie-Minghui

relational matirx is very sparse in Chinese dataset. When I tested my implemention of multi_head_selection, the loss of relation was very small. Because most relations were 'N', the samples are...

Results on WebquestionSP can't reimplement, 0.71 in Paper, but 0.608 I run

9

I run the code using the same random seed. (I don't change your code), the final results are as follows:  1-hop accuracy is 0.732, 2-hop is 0.445, the total...

这个问题是指如何选择c中的k（归并排序中使用插入排序），而不是单独比较插入排序和归并排序。我认为答案应该是k < logn是归并中使用插入。

I think the complexity of your code in 2.3-7 whose complexity you say is O(n), is actually O(nlogn), because the complexity of inserting a element into map is log(n). You...