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

### Describe the bug The F-scores shown after training a SequenceTagger model with FlairEmbeddings are way higher than when loading the model from file and doing an evaluation on it....

bug

### Question Hi everyone, I would like to experiment with the Biaffine/SpanTagger implementation that is e.g. used in the great [CleanCoNLL](https://aclanthology.org/2023.emnlp-main.533.pdf) paper. I could reproduce the results using FLERT, but...

question

### Question I'm trying to resume training according to : [This code](https://github.com/flairNLP/flair/blob/8bcc3d9dac0b0e318e0bd0290af5a36f4d414fab/resources/docs/TUTORIAL_TRAINING_MORE.md?plain=1#L73) where it says : # 7. continue training at later point. Load previously trained model checkpoint, then resume...

question

### Question I use flairNLP to annotate nested entities. Currently, I'm experimenting to use different models for different syntactic layers. My plan to do so was, to be a bit...

question

There was a bug where in a batch, it took the last tag sequence of that batch from the Viterbi decoder instead of the tag sequence corresponding to its sentence.

bug

### Question I just noticed a paper that came out this month on arxiv titled: **xLSTM: Extended Long Short-Term Memory** It looks like the **Algorithm** that was the original success...

question

### Question How can I correctly train two tasks simultaneously on a single corpus using the parameter use_all_task=True? When I attempted to train two models together on one corpus, I...

question

### Question Hi, I'm training a SequenceTagger to do the NER task using my customed dataset with the customed features. After training was done, I got a file named test.tsv...

question

### Describe the bug I'm trying to port an AllenNLP model to a framework that's still maintained so am considering `flair`. My original model is a character LSTM based tagger....

bug

https://github.com/flairNLP/flair/issues/3474 Adds random seed parameters to dataset splitting and downsampling functions