scibert

scibert copied to clipboard

Problem with datasaet

5

where is the result on dataset citation_intent and mag in paper?

HaodaY

Better performance than the reported.

1

Hi, I am reproducing the fine-tune results following your instruction. I work on your default code and my setting is as below. I work on ebmnlp and pico task without...

shizhediao

Hi, I noticed something weird about the `max_len` attribute of the `tokenizer` ```python from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("allenai/scibert_scivocab_uncased") print(tokenizer.max_len) # => 1000000000000000019884624838656 ``` Whereas I expected it to...

JohnGiorgi

https://github.com/allenai/scibert/blob/ae9f98f58a9793781148ccf715b03f7160060f24/scibert/models/bert_text_classifier.py#L37 BertTextClassifier requires an instance of TextFieldEmbedder and calls `get_output_dim` on that instance, however that method always raises NotImplementedError. Is this meant to deliberately un-implement a method from the superclass,...

swfarnsworth

https://github.com/allenai/scibert/blob/ae9f98f58a9793781148ccf715b03f7160060f24/scibert/models/bert_text_classifier.py#L27 I believe that this line should read `verbose_metrics: bool = False`. As it stands, it doesn't have a default value.

swfarnsworth

Traceback (most recent call last): File "/home/hui2019/scibert-master/scibert-master/src/allennlp/allennlp/common/util.py", line 289, in get_spacy_model spacy_model = spacy.load(spacy_model_name, disable=disable) File "/home/hui2019/anaconda3/envs/py36_pytorch1.3.1/lib/python3.6/site-packages/spacy/__init__.py", line 27, in load return util.load_model(name, **overrides) File "/home/hui2019/anaconda3/envs/py36_pytorch1.3.1/lib/python3.6/site-packages/spacy/util.py", line 139, in load_model...

ghost

AttributeError while using SciBERT

3

`` import tensorflow as tf from transformers import * #BertTokenizer, TFBertModel tokenizer = AutoTokenizer.from_pretrained('allenai/scibert_scivocab_uncased') model = AutoModel.from_pretrained('allenai/scibert_scivocab_uncased') input_ids = tf.constant(tokenizer.encode("My dog is cute"))[None, :] # Batch size 1 outputs =...

Saichethan

SciBERT Corpus Availability?

2

Hi, do you plan to make the pretraining corpus available, or provide a way to reproduce / approximate it using Semantic Scholar?

CyndxAI

How to change paramaters when build own RE model?

4

We'd like to build a specific RE model to meet our own requirement. The performance is quite good. However, we identified some overfitting problems and we'd like to solve the...

transpurs

 what's the wrong,I only modify the path .

zwd13122889