README.md

metadata

datasets:
  - 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
language:
  - en
metrics:
  - accuracy
  - f1

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 has learn can detect NER spans (with no differenciation on classes). Labels use the IBO format and are:

• 'B-TAG': beginning token of span
• 'I-TAG': inside token of span
• 'O': token not a span

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	0.964