On Generalization in Coreference Resolution
Paper • 2109.09667 • Published
How to use shtoshni/longformer_coreference_joint with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="shtoshni/longformer_coreference_joint") # Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("shtoshni/longformer_coreference_joint")
model = AutoModel.from_pretrained("shtoshni/longformer_coreference_joint")YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Longformer-large model finetuned for the coreference resolution task. The model is fine-tuned over a mixture of OntoNotes, LitBank, and PreCo. The model is released as part of this paper. Note that the document encoder is to be used with the rest of the model parameters to perform the coreference resolution task. For demo purposes, please check this Colab notebook.