NRE

NRE copied to clipboard

about test.h in CNN+ATT

2

Hi, in /CNN+ATT/test.h, line [114](https://github.com/thunlp/NRE/blob/6e50eb9603144eedf67152fe22c9a64a9076a3a0/CNN%2BATT/test.h#L114), it seems that the function `vector test(int *sentence, int *testPositionE1, int *testPositionE2, int len, float *r)` is never used, since `vector score` is never used...

ShellingFord221

train.cpp: error: reference to 'end' is ambiguous

5

train.cpp: error: reference to 'end' is ambiguous error message appears when compile. Please take a look at the screenshot. Environment: Mac Apple LLVM version 8.1.0 (clang-802.0.42)

sylviawangfr

P@N是什么意思呀，N代表什么

cswangjiawei

 我不理解公式中的矩阵A，什么是带权对角矩阵，矩阵元素的值是作为参数训练还是一开始就固定？

cswangjiawei

你好，现在大多模型在输入的时候都采取了将句子按照实体划分为3段的方法，这个时候每段的长度可以pad或者trancate到定长。假如我使用trancate的方法，那么两个实体间的部分怎么trancate呢？ 比如XXX Obama XXXXXXXXXXXXX USA XXX. Obama左边和USA右边部分如果太长的话可以删掉远离实体的单词，但是Obama和USA中间的部分怎么处理呢？谢谢！

ShellingFord221

I try to reproduce the cnn/pcnn with tensorflow. In test phase, I treat a sentence as a special bag, and draw Precision-Recall curve. Surprisingly, single CNN/PCNN get better performance than...

onehaitao

My file like this: V70驱动器报警F30001过电流” 电机动力电缆干扰

lewistf

求教：ubuntu16.04 编译后，执行命令./test后，出现段错误

2

ubuntu16.04 编译后，执行命令./test后，出现段错误

ShannGit

How to select relation in Attention while Testing?

13

Hi, some thing about the attention confused me a lot.  the **r** is the query vector with relation r (the relation representation). In train phase, is it **r** is...

ShomyLiu

Calculate gradients and update parameters for CNN+ATT

1

For the code at: https://github.com/thunlp/NRE/blob/master/CNN%2BATT/train.cpp I can not follow how to calculate gradients and update parameters, maybe from line 193 to line 238. Could anyone explain, please? @Mrlyk423

pvthuy