-
Seems like
https://github.com/zalandoresearch/flair/blob/master/flair/embeddings.py#L139
Does not make use of the OoV functionality present in FastText, seems like it would be a nice addition!…
-
I am wondering if there is a way to pass more than one document through `DocumentPoolEmbedding` at a time?
my current code:
```
from flair.embeddings import WordEmbeddings, FlairEmbeddings, Docum…
-
Please fill out the form below.
### System Information
- Framework : Pytorch
- Framework Version: 1.0.0
- Python Version: 3.5/3.6
- **CPU or GPU**: CPU
- **Python SDK Version**: Not sure
- Ar…
-
I'm trying to understand what stacking two embeddings entails? Does it mean that the embeddings are concatenated, or does it have something to do with the combination of outputs from two different emb…
-
HI, I seems that no cuda_available in trainer.py, wouldn't the model support to train on GPU?
-
i tried to stack elmo , bert , word , flair embeddings using document embedding and tried to find the cosine similarity between two sentences after embedding the sentences i get really very bad rco…
-
**Problem**
I'm using the DocumentPoolEmbeddings class in order to embed abstracts. I'm using an approach to distribute the calculation with dask on several workers. On my local machine, I can embe…
-
**Describe the bug**
I am using FLAIR (great software, thanks a lot!) to get BERT embeddings.
For a given input, I get different BERT embeddings every time I run the code.
This might be a PyTo…
-
This is a code that I am using:
```
from flair.embeddings import CharacterEmbeddings
c_embeddings = CharacterEmbeddings ()
word_string_1 = "Example"
word_string_2 = "Example"
c_embeddings_…
-
**Describe the bug**
I am trying to continue the training of the `news-forward` language model on domain specific data, which works in a jupyter notebook but fails when executing the code in a plain …