ganjinzero/triaffine-nested-ner

Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition [ACL 2022 Findings]

triaffine-nested-ner's Issues

Not Found for url: https://huggingface.co/pretraining-models/biobert_v1.1//resolve/main/config.json

Could u please offer other source url ?

请问代码是不公开了吗

Question about data format

I am trying to apply the model to other data corpus. I was curious that what is your input data format. How could I preprocess the data and then pass to the model? Thank you.

I'm getting an f1 score of zero.

Hello,
I want firstly to thank you for making your code publicly available.
Actually, I was trying to reproduce your code using ACE04 dataset (I'm using only the samples provided here, since I don't have access to the dataset). But I'm getting an f1 score of 0.
Dev_Epoch24 {'p': 0, 'r': 0, 'f1': 0}

Do you have any insights on what might be causing the problem?
Thank you!

Cuda out of memory error for another dataset for a 45 Gb GPU

Can you tell anything that i can do to run it successfully ?

File "model5/Triaffine-nested-ner/model/span_att_v2.py", line 405, in get_class_position
score = contract('bxi,bzrk,ikjr,bxj->bzxr', x3, h_span3, self.parser_list[0].parser1.weight, y3)
File "anaconda3/envs/model5/lib/python3.7/site-packages/opt_einsum/contract.py", line 507, in contract
return _core_contract(operands, contraction_list, backend=backend, **einsum_kwargs)
File "anaconda3/envs/model5/lib/python3.7/site-packages/opt_einsum/contract.py", line 573, in _core_contract
new_view = _tensordot(*tmp_operands, axes=(tuple(left_pos), tuple(right_pos)), backend=backend)
File "anaconda3/envs/model5/lib/python3.7/site-packages/opt_einsum/sharing.py", line 131, in cached_tensordot
return tensordot(x, y, axes, backend=backend)
File "anaconda3/envs/model5/lib/python3.7/site-packages/opt_einsum/contract.py", line 374, in _tensordot
return fn(x, y, axes=axes)
File "anaconda3/envs/model5/lib/python3.7/site-packages/opt_einsum/backends/torch.py", line 54, in tensordot
return torch.tensordot(x, y, dims=axes)
File "anaconda3/envs/model5/lib/python3.7/site-packages/torch/functional.py", line 936, in tensordot
return _VF.tensordot(a, b, dims_a, dims_b) # type: ignore

RuntimeError: CUDA out of memory. Tried to allocate 10.69 GiB (GPU 0; 44.40 GiB total capacity; 34.47 GiB already allocated; 8.00 GiB free; 35.18 GiB reserved in total by PyTorch)

请问代码什么时候公开呢