flair icon indicating copy to clipboard operation
flair copied to clipboard

A very simple framework for state-of-the-art Natural Language Processing (NLP)

Results 253 flair issues
Sort by recently updated
recently updated
newest added

First PR about https://github.com/flairNLP/flair/issues/2640: refactoring models, such that each model has a `_prepare_tensors` and a `forward` method, where one extracts all tensors out of the data points and the latter...

Following the comment in #2888, experiment with alternative heuristic that distinguishes between embeddings and all other parts of the model.

I am using Hunflair and having below error while running it: Can anyone suggest me the next step? Traceback (most recent call last): File "hunflair.py", line 35, in hunflair =...

question

Hello, I am working on a NER model in Spanish, I want to fine tune the [(flair/ner-spanish-large)](https://huggingface.co/flair/ner-spanish-large) model that is already trained to add certain tags to words that this...

question

Hi, I saw related topic [here](https://github.com/flairNLP/flair/issues/2465). I tried to bring pre-trained (as well as fine-tuned) LayoutLMv2 embeddings into Flair but was not successful as expected. I tried to mimic "class...

`TransformerWordEmbeddings` with `distilbert-base-uncased` cannot embed an empty token if at the end of a sentence: ```python # sentence with two empty tokens, one at end sentence = Sentence(["hello", " ",...

Good evening, I'm trying to use Flair to convert some texts into sequences of POS tags. In order to do so, partly following the HuggingFace documentation (https://huggingface.co/flair/pos-english), I'm doing the...

question

I would like to perform the NER task for my problem. I would like to know if NER uses POS Tagging knowledge in any way during the process. If not,...

question

As per **#2407** (https://github.com/flairNLP/flair/issues/2407) the Tagger complains that some input tokens are not in the dictionary (despite add_unk=True). This can easily be recreated by having a tag exist in your...

bug

I've been debugging bad output from the pretrained model. What corpus is this trained on? How to make it not overfit. ``` import flair # !pip install GIT+https://github.com/flairNLP/flair.git flair_sentiment =...

bug
wontfix