-
Hello,
This is an enhancement request. We are currently exploring predictions, and currently it's hard to refer to rules linked to a prediction other than something like "the fourth from the top" o…
-
I read from line 141 in main.py about label smoothing:
```
e2_multi = ((1.0-args.label_smoothing)*e2_multi) + (1.0/e2_multi.size(1))
```
Isn't it should be the following instead？
```
e2_multi …
-
Nice work, I have some questions about the training process of KGT5.
(1) 1 vs ALL method: The KGT5 model is trained using the 1 vs ALL method, but the loss function in main_accelerate.py is CE.
(2) …
-
```
Python: 3.8.5
Torch: 1.7.1
Cuda: 11.0 (yet it was disabled through CUDA_VISIBLE_DEVICES)
```
I got few problems with data types (torch `Embeddings` required `LongTensor` instead of `IntTens…
-
My results on the wn18rr dataset are particularly low, with more than ten points missing for each metric. I 've seen this problem in the past, but I can 't find PromptKG/toolkit
![image](https://gith…
-
你好作者，由于ConvE原作者的代码我实在跑不通，我参考了你的代码，收获很多，十分感谢。但是在WN18RR数据集上运行ConvE的时候，未能达到预期的结果。原文章的MRR能达到0.43，但是我尝试了很多次，MRR都停在0.32左右。请问你跑的结果如何？
-
Hello,
I wish to work RNN-Logic model and do some analysis with it. But unfortunately, I do not have resources to train the RNN-Logic model for FB15K-237 and WN18RR datasets right now. Would it be …
-
您好，可以提供一份表4中的尾实体预测的代码吗？
-
In the paper you explicitly mentioned that you trained a BPE tokenizer for your experiments:
![image](https://user-images.githubusercontent.com/43718473/231147502-69eb29ae-9fbb-491e-b119-4a23cf9c01…
-
Hello,
Thank you for providing the code of your paper. As per the instructions, I am running the code for Version 2 of RNNLogic with emb. While the training is running as expected, it is very slo…