-
Use the Turkish corpus provided by Onur using pytorch-pretrained-BERT.
-
Hi,
The language model is trained on 1-billion word corpus, I want to continue train them on my specific domain corpus, can I do that in flair?
Thanks!
-
For text classification, the format is follows -
__label__
As per my understanding, the text/document is converted to it's word embedding format . But what about the categorical labels ? i.e. are…
-
Elmo now has a new model trained on the PubMed corpus, check ( https://allennlp.org/elmo under contributed model)
Is this supported in Flair the same way the others (original, medium, small and Portu…
nstfk updated
5 years ago
-
Hi
Any suggestions on How i could improve NER perfomance, i am training it on custom data.Apart from trying out different Embeddings, What else can i try?
Thanks in advance, and any suggestions…
-
PS Very New Flair User :)
Can't increase the num_workers...
**To Reproduce**
```
document_embeddings = DocumentRNNEmbeddings(word_embeddings,
hidde…
-
Due to issue #184, CharLMEmbeddings.train() has been overridden:
```python
def train(self, mode=True):
pass
```
But this prevents it from switching to eval mode, causing that the drop…
-
In DocumentRNNEmbedding the sentences in the batch are permuted (sorted) to take advantage of PyTorch's `pack_padded_sequence` and `pad_packed_sequence` require sentences ordered by length. In the res…
-
Now that flair has been trained with different embeddings and optimized parameters, it should be trained with different embeddings and learning rates, with other parameters being below:
* hidden_si…
-
Thanks for releasing BERT!
I'm just wondering if BERT will be available on TensorFlow Hub like ELMO (for either fine-tuning or extracting features)?