tonytan48 KD-DocRE issues

tonytan48 / KD-DocRE

Implementation of Document-level Relation Extraction with Knowledge Distillation and Adaptive Focal Loss

110 stars 20 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

有没有正在跑代码的人可以互相交流一下

#25 QiyiJiang opened 6 months ago
0
why can't i find the axial_attention from code"from axial_attention import AxialAttention". the code is incomplete whitout this ,

#24 Deargoodnight opened 1 year ago
1
frequent/longtail relation

#23 JZBZ2020 opened 1 year ago
3
请问可以给一下你们训练环境的requirements.txt吗？

#22 dragondog129 closed 1 year ago
2
GPU resources

#21 Shike-Cheng closed 1 year ago
0
batch_roberta.sh

#20 YjwHello closed 1 year ago
2
terminated

#19 XingYu131 opened 1 year ago
2
Failed to train the model

#18 LeeReeny opened 1 year ago
2
My reproduction results (with distant supervision) are lower than results in the paper.

#17 Jize-W closed 1 year ago
1
Question about the focal loss

#16 RedVelvetCake21 closed 1 year ago
2
Sample code to run inference on any text

#15 AlexisNvn opened 2 years ago
1
I'm curious that after downloading the file, the content is empty.

#14 WilliamAntoniocrayon closed 2 years ago
2
Confused about not reproducing the results.

#13 msa30 closed 2 years ago
13
the program will always be killed.

#12 WilliamAntoniocrayon closed 2 years ago
3
I got the problem about "ZeroDivisionError: float division by zero"

#11 WilliamAntoniocrayon closed 2 years ago
2
A confusion happened in bash inference_logits_roberta

#10 cuberJ closed 2 years ago
1
I'm confusing about KD-DocRE/scripts/

#9 WilliamAntoniocrayon closed 2 years ago
4
An error occurred while performing the step 2

#8 WilliamAntoniocrayon closed 2 years ago
2
knowledge_distill part script not found

#7 WatsonWangZh closed 2 years ago
1
ModuleNotFoundError: No module named 'multihead_attention'

#6 moh-yani closed 2 years ago
2
ModuleNotFoundError: No module named 'utils'

#5 moh-yani closed 2 years ago
2
Adaptive Focal Loss

#4 Hou-jing closed 2 years ago
1
I want to get the code in this paper

#3 WilliamAntoniocrayon closed 2 years ago
1
Why not compare with SSAN-KD-Rb-l models that use knowledge distillation strategy?

#2 WatsonWangZh closed 2 years ago
1
Would you tell me when will you upload the code?

#1 1120161807 closed 2 years ago
1