flair
flair copied to clipboard
flairNLP
A very simple framework for state-of-the-art Natural Language Processing (NLP)
I thought of `Fine-Tuning` the model `flair/ner-english-ontonotes` here `https://huggingface.co/flair/ner-english-ontonotes`. I couldn't find the following files in `Files and Verions` https://huggingface.co/flair/ner-english-ontonotes/tree/main - tokenizer_config.josn - config.json - some more tokens related files...
A proposal to return the loss per sentence. This way, it would be easier to compute uncertainty scores used for [active learning](https://arxiv.org/abs/1707.05928). I made experience in prior projects, that that...
A clear and concise description of what you want to know. embeddings_storage_mode of mine is always cpu when using searchspace to optimise
When doing sequence tagging for Named Entities, Flair is injecting spaces around punctuation inside the Span itself (which I suspect this is due to the tokenization being applied). I previously...
Is there an updated version of few shot multi-label classifier (trained on tars-base)? Was referring to the article below (however did not get the desired results): [https://towardsdatascience.com/zero-and-few-shot-learning-c08e145dc4ed](https://towardsdatascience.com/zero-and-few-shot-learning-c08e145dc4ed) Modified the code...
When doing sequence tagging for Named Entities, Flair is injecting spaces around punctuation inside the Span itself (which I suspect this is due to the tokenization being applied). It would...
I have a GPU instance with 8 GPUs. I want to use the GPUs combined since using one cuda device is giving me constant cuda OOM error. The training seems...
**Describe the bug** `token.get_label` return wrong tags **To Reproduce** First we have a corpus to read, the training data `train_datapool_sample.txt` is like below. ``` Germany NNP B-NP B-LOC imported VBD...
**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior (e.g. which model did you train? what parameters did you...
