hugging face models do not work

[MHDBST]

Hi,
Thanks for your great contribution in biomedical domain.
I tried all the models in the hugging face format and I couldn't replicate any of the results or even get a reasonable output. Is there something wrong with the code, model, or anything is missing?

I run the following code:

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("razent/SciFive-base-PMC")  
model = AutoModelForSeq2SeqLM.from_pretrained("razent/SciFive-base-PMC")
model.to(device)
sentence = "Identification of APC2 , a homologue of the adenomatous polyposis coli tumour suppressor ."
text =  "ncbi_ner: " + sentence + " </s>"

encoding = tokenizer.encode_plus(text, pad_to_max_length=True, return_tensors="pt")
input_ids, attention_masks = encoding["input_ids"].to(device), encoding["attention_mask"].to(device)

outputs = model.generate(
    input_ids=input_ids, attention_mask=attention_masks,
    max_length=256,
    early_stopping=True
)

for output in outputs:
    line = tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True)
    print(line)

And this is the output:

ncbi_ner: ncbi_ner: ncbi_ner:

The expected output (based on the paper) should be as follow:

Identification of APC2 , a homologue of the entity* adenomatous polyposis coli tumour *entity suppressor .

I replaced the model with all other available large, base, pubmed, pmc, pubmed+pmc models (basically all 6 hugging face variations) but I didn't get any reasonable outputs.

Could you give me a solution?

[justinphan3110]

Hi Sorrry for the late reply, the models on HuggingFace is just pretrained weights. We didn't share the fine-tuned models. you can fine-tuned it using this scrip with mesh tensorflow here https://github.com/justinphan3110/SciFive/blob/main/finetune/ner/scifive_fine_tune_ner.ipynb

[justinphan3110]

Let me know if you still need the fine-tuned models, I can upload it into huggingface for you

[kletinic]

Hi Justin, can you please upload a fine tuned model for biomedical QA (the one that outperformed BioBert in your paper)? It'd be great - Thanks!

[nguyennth]

Hi,

Thank you for publishing the models. I'm wondering if the current models on HuggingFace are still the pretrained weights as you said in March? I used the example code there (https://huggingface.co/razent/SciFive-base-Pubmed_PMC) but couldn't reproduce the same output shown in your paper. Given the input of "Identification of APC2 , a homologue of the adenomatous polyposis coli tumour suppressor .", I got an output of ', a novel tumour suppressor, in human colon cancer............................:::::::::. :::.::.'

If the current published models are not the fine-tuned ones, could you please published those fine-tuned models for NER?

Thank you in advance for your reply!