Instructions to use RJ3vans/NPheadTagger with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RJ3vans/NPheadTagger with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="RJ3vans/NPheadTagger")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("RJ3vans/NPheadTagger") model = AutoModelForTokenClassification.from_pretrained("RJ3vans/NPheadTagger") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Input a noun phrase (NP) and the model will tag its syntactic head as HEAD. Non-head tokens will be tagged as NA.
The model is intended to tag multiple heads in compound NPs. It is not intended to tag all heads in complex NPs.
The training data is derived from a dataset in which NPs are identified using the Berkeley neural parser which does not identify the heads of syntactic constituents. The training data includes erroneous NPs in which each token is tagged as ERROR.
Examples you might try include:
The bottle of ginger beer
John, Peter, and Mary, who live in Sri Lanka
The man who won the race
- Downloads last month
- 8