wzhouad / ATLOP

Source code for paper "Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling", AAAI 2021

wzhouad/ATLOP Issues

The usage of the ATLoss
Updated 2 years ago
The results of ATLOP based on the bert-base-cased model on the DocRED dataset
Closed 3 years ago11
What is the computational complexity of the ATLOP model?
Closed 3 years ago1
Mention embedding
Closed 3 years ago4
end_tokens for RoBERTa?
Closed 3 years ago1
about L2R and R2L
Updated 3 years ago4
About the process_long_input.py
Closed 3 years ago3
--save_path issue
Updated 3 years ago
How to get test score？
Closed 3 years ago1
about the labels
Closed 3 years ago4
The best results of same random seed are different at each time when I trained the ATLOP
Closed 3 years ago4
Using a fixed seed doesn't seed to work
Closed 4 years ago2
Did your model trained on DocRED's train_distant.json?
Closed 3 years ago1
Apply model on free text data
Closed 3 years ago1
How should I be running the Enhanced BERT Baseline model?
Closed 3 years ago2
Where did the "/meta/rel2id.json" come from?
Closed 3 years ago2
Inference
Closed 3 years ago1
The main purpose of the function: get_label
Closed 3 years ago5
About baseline implementation and results in the paper
Closed 3 years ago2
The problem of setting environment
Closed 3 years ago1
Instruction to extract relation on a custom dataset
Closed 3 years ago
How to get the rel2id.json
Closed 3 years ago2
Can you please release trained model?
Closed 3 years ago3
Why do we not recalculate recall for the ignored setting?
Closed 3 years ago2
Is there a reason why the lengths of each chunk for the CDR dataset is 17 and not 23?
Closed 3 years ago2
Training on custom dataset
Closed 4 years ago1
Multi-gpu code
Closed 4 years ago1
model.py
Closed 4 years ago5
Any plans to release the codes for CDR?
Closed 4 years ago4
Question regarding 'max-seq-length'
Closed 4 years ago2