Liu Zhihui

I forked your code and add support for Task 8 data. The test accuracy now is 49.50%, while the accuracy of CNN model without position embedding is 59.15%. Can you...

I will try.

@JinJiao8 我按照论文中实现的，结果性能不太好，我也不清楚原因。

I can't reproduce the results of the paper, maybe the code is not right. I don't know what's wrong.

@lawlietAi What is your test accuracy?

@allanj no one.

@GatsbyUSTC If an entity contains several words, we just use the last word to represent the entity. It is a common practice.

@GatsbyUSTC Attention on words try to find the most relevant words related to the entity pair, of course it will help. Take the relation "President" as an example, the word...

@GatsbyUSTC The inner product does not guarantee that the two words must be similar semantically. It can also be interpreted as relevance since the embeddings are learned. "with + n."...

It is just a hyperparameter. 123 is related to 60. The actual relative distance is : 60, a total of 123.