Downloads · 30 days
7
1% of all-time downloads
roberta-span-detection
AntoineBlanot/roberta-span-detection
roberta-span-detection is a token classification model from AntoineBlanot. Use it when you need labels on individual words, such as names. It is set up for transformers.
This model is a fine-tuned model of roberta-large after being trained on a mixture of NER datasets.
All-time downloads
1.1K
Public
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.4 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- May 24, 2023
- Updated
- Jun 5, 2023
- SHA
- 44543bef
Try a prompt
Model card
From the Hugging Face model README
RoBERTa Span Detection
This model is a fine-tuned model of roberta-large after being trained on a mixture of NER datasets.
Basically, this model can detect NER spans (with <u>no differenciation on classes</u>). Labels use the IBO format and are:
- 'B-TAG': beginning token of span
- 'I-TAG': inside token of span
- 'O': token not a span
Usage
This model has been trained in an efficient way and thus cannot be load directly from HuggingFace's hub. To use that model, please follow instructions on this repo.
Data used for training
- tner/bc5cdr
- tner/bionlp2004
- tner/btc
- tner/conll2003
- tner/fin
- tner/mit_movie_trivia
- tner/mit_restaurant
- tner/multinerd
- tner/ontonotes5
- tner/tweebank_ner
- tner/tweetner7
- tner/wikineural
- tner/wnut2017
Evaluation results
| Data | Accuracy |
|---|---|
| validation | 0.972 |
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- Languages
- en
- Created
- May 24, 2023
- Updated
- Jun 5, 2023